JP2004126813A - Personal identification system, personal identification method, entry/exit management system and entry/exit management method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve operability by enabling a user to update a dictionary only by inputting personal identification information once, and stabilize the performance and accuracy of face matching processing. <P>SOLUTION: If 1:N face matching fails to match the face, an input of personal identification information is required. If the degree of matching between face data corresponding to input personal identification information and a shot face image is a given value or greater, the face data are updated. <P>COPYRIGHT: (C)2004,JPO

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to, for example, a personal authentication device and a personal authentication method for performing personal authentication by photographing a face image of a person and comparing the photographed face image with a face image registered in a dictionary in advance. The present invention relates to an entry / exit management system and an entry / exit management method using the personal authentication device or the personal authentication method.
[0002]
[Prior art]
Conventionally, an image (hereinafter, referred to as a face image) including at least a face of a person to be authenticated (a person to be authenticated, a passerby) is photographed, and the photographed face image is compared with face data registered in a dictionary in advance. There is a personal authentication device for performing personal authentication. In such a personal authentication device, when updating face data (dictionary data) registered in a dictionary, a person to be updated first inputs personal identification information (ID information) for identifying the person. . As a result, the personal authentication device specifies an individual based on the input personal identification information, and performs personal authentication by comparing the dictionary data of the specified individual with the face image of the photographed person.
[0003]
When such personal authentication is successful, the personal authentication device updates the dictionary data of the person specified by the personal identification information with the captured face image. Further, when the personal identification is not successful in the face matching, the personal authentication device further requests the individual to input personal authentication information (such as a password) for authenticating the individual. If the personal authentication information input by the person in response to this request is correct, the personal authentication device lowers the threshold for face matching and performs the face matching process again. If the person can be identified by the face matching process, the face data of the person is updated.
[0004]
However, in the personal authentication device as described above, it is necessary to input personal identification information, personal authentication information, and the like to the target person several times in order to specify the person who updates the dictionary. For this reason, the operability is poor, and it is troublesome for the user to update the dictionary data.
Also, when performing face matching by inputting personal identification information first, the person to be compared is uniquely identified by the personal identification information, so a person with a similar face may be incorrectly authenticated. May increase. In this case, if the personal identification information is used for a person with a similar face, the possibility that the dictionary data is intentionally updated increases, and the security performance decreases.
In addition, since the update of the dictionary data is updated irrespective of the intention of the user, it is unclear for the user whether or not the dictionary data has been updated.
[0005]
[Patent Document 1]
Japanese Patent Application Laid-Open No. H10-31462
[Problems to be solved by the invention]
As described above, it solves the problem that the operability when updating face data is poor and the security performance is reduced, and the operation of the user when updating the previously registered face data is solved. It is an object of the present invention to provide a personal authentication device, an entry / exit management device, a personal authentication method, and an entry / exit management method, which simplify simplification, improve operability, and improve security and accuracy of personal authentication.
[0007]
[Means for Solving the Problems]
The personal authentication apparatus of the present invention performs personal authentication using at least an image including a face, and includes a registration unit in which face data of a person and personal identification information for specifying the person of the face data are registered; A photographing means for photographing an image including at least the face of the authenticator, and a collation for determining the degree of collation between the image containing at least the face of the person to be authenticated photographed by the photographing means and the face data registered in the registration means. Means for authenticating the subject to be authenticated as a person having the maximum collation degree when the maximum collation degree among the collation degrees determined by the collation means is equal to or greater than a predetermined first threshold value. Authentication means, and guidance means for guiding input of personal identification information to the person to be authenticated when the maximum collation degree among the collation degrees determined by the collation means is smaller than the first threshold value, and the guidance means If the degree of matching with the face data of the person corresponding to the personal identification information input by the person to be authenticated in response to the guidance is equal to or greater than a predetermined second threshold value smaller than the first threshold value, A second authentication unit that authenticates the person identified by the personal identification information, and authenticates the subject to be identified by the personal identification information by the second authentication unit. In the case, there is provided updating means for updating face data corresponding to the personal identification information registered in the registration means using an image including at least a face taken by the photographing means.
[0008]
An entry / exit management device according to the present invention manages entry / exit of a person using at least an image including a face, and includes face data of a person who is allowed to pass in advance and personal identification information for identifying the person of the face data. Registration means in which is registered, a photographing means for photographing an image including at least a face of a passerby, an image including at least a face of a passerby photographed by the photographing means, and a face registered in the registration means. A matching means for determining the degree of matching with the data, and a first traffic permitting the passerby when the maximum matching degree among the matching degrees determined by the matching means is equal to or greater than a predetermined first threshold. Permission means; guidance means for guiding the passer-by to input the personal identification information when the maximum collation degree among the collation degrees determined by the collation means is smaller than the first threshold value; When the degree of matching with the face data of the person corresponding to the personal identification information input by the passer-by in response to the guidance is equal to or greater than a predetermined second threshold smaller than the first threshold, A second traffic permitting means for permitting the traffic, and when the traffic of the passer is permitted by the second traffic permitting means, the second traffic permitting means is registered in the registering means by using an image including at least a face photographed by the photographing means. Updating means for updating face data corresponding to the personal identification information.
[0009]
The personal authentication method according to the present invention is a method used in a personal authentication device that performs personal authentication using an image including at least a face, and includes a photographing step of photographing an image including at least a face of a person to be authenticated, A collation step of judging the degree of collation between an image including at least the face of the person to be authenticated photographed by the user and face data of a person registered in advance in correspondence with personal identification information for identifying the person in the registration means; A first authentication step of authenticating that the person to be authenticated is a person having the maximum collation degree when the maximum collation degree among the collation degrees determined in the collation step is equal to or more than a predetermined first threshold value; In the case where the maximum collation degree among the collation degrees determined in the collation step is smaller than the first threshold, a guidance step of guiding the person to be authenticated to input personal identification information, hand When the degree of collation with the face data of the person corresponding to the personal identification information input by the person to be authenticated is equal to or greater than a predetermined second threshold smaller than the first threshold, the person to be authenticated is identified by the personal identification information. A second authentication step of authenticating that the person to be identified is a person identified by the personal identification information, and a second authentication step of authenticating the subject by the second authentication step. Updating the face data corresponding to the personal identification information registered in the registration means using an image including at least a face photographed in the step (a).
[0010]
The entry / exit management method of the present invention is a method used for an entry / exit management device that manages the entry / exit of a person using an image including at least a face, and a photographing step of capturing an image including at least a face of a passerby. And comparing the image including at least the face of the passerby photographed in this photographing process with the face data of a person who is permitted to pass and registered in advance in the registration means corresponding to the personal identification information for specifying the person. A collation step of judging a degree, a first traffic permitting step of permitting the passerby to pass when the maximum collation degree among the collation degrees determined in the collation step is equal to or greater than a predetermined first threshold value, In the case where the maximum collation degree among the collation degrees determined in the collation step is smaller than the first threshold value, a guidance step of guiding the passer-by to input the personal identification information, and When the degree of matching with the face data of the person corresponding to the personal identification information input by the passer is equal to or greater than a predetermined second threshold smaller than the first threshold, a second pass permitting the passer When the passer is allowed to pass by the permitting step and the second pass permitting step, the passerby responds to the personal identification information registered in the registration means using an image including at least a face taken in the photographing step. And updating the face data to be updated.
[0011]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram illustrating an example of an entry / exit management device (personal authentication device) according to an embodiment of the present invention.
As shown in FIG. 1, the entry / exit management device includes a user interface (I / F) unit 1, an authentication device main body 2, and a door opening / closing mechanism 3. The user interface unit 1 and the authentication device main body 2 may be integrally formed.
The user interface unit 1 is installed near a door (not shown) to a security area such as a room for entry / exit management. As shown in FIG. 1, the user interface unit 1 includes a camera (photographing unit) 11, a display unit (notifying unit) 12, an operation unit 13, an illumination 14, and the like.
[0012]
The camera 11 captures a face image of a person to be authenticated (authenticatee, passerby). As the camera 11, for example, an industrial color camera (a video camera using a CCD or CMOS image sensor) is used. The camera 11 may be a camera that captures a monochrome image. The display unit 12 displays an image being photographed, guidance for a user, and the like. The operation unit 13 includes a numeric keypad and the like. The operation unit 13 is used by the person to be authenticated to input personal identification information such as a personal identification number. The illumination 14 illuminates a person's face or the like captured by the camera 11. The illumination 14 functions as an auxiliary illumination when the camera 11 captures a face image of the person to be authenticated.
[0013]
The authenticator main body 2 performs personal authentication processing and the like, and is connected to each unit of the user interface unit 1 and the door opening / closing mechanism 3. As shown in FIG. 1, the authenticator body 2 includes a processing unit 21, an image input unit 22, an image memory 23, a display control unit 24, an operation unit interface (I / F) 25, a lighting control unit 26, and a door control unit. (Traffic permitting means) 27, dictionary (registering means) 28, and the like.
[0014]
The processing unit 21 controls the entire entry / exit management device. The processing unit 21 performs face image detection processing, face feature amount extraction processing from face images, face image matching processing (matching means), and authentication processing (based on a program stored in a program memory (not shown)). It has a function of performing processing such as authentication processing) or update processing (update means) for data in the dictionary 28. The image input section 22 is an interface that takes in an image taken by the camera 11 into the authentication device main body 2. The image input unit 22 stores an image captured from the camera 11 in an image memory 23. The image memory 23 stores, for example, images captured by the camera 11 and captured into the authentication device main body 2 via the image input unit 22.
[0015]
The display control unit 24 controls display of the display unit 12. The operation section interface 25 captures information input by the operation section 13. The lighting control unit 26 controls turning on and off of the lighting 14. The door control unit 27 controls opening and closing of the door by the door opening and closing mechanism 3. The dictionary 28 is used as the face collation dictionary, and corresponds to face data such as a face image of a registrant (a person who is allowed to enter and exit the security area (pass through a door)), and to each face data. The personal identification information of the person is stored. Here, it is assumed that a face image and personal identification information of a person who is permitted to enter the security area in the door controlled by the door control unit 27 are stored. Further, the dictionary 28 may store, as face data, a face feature amount of a registrant's face image to be matched with a face feature amount extracted from an image captured by the camera 11. Note that the dictionary 28 may be provided outside the authentication device main body 2 or may be provided on an external device that can communicate via a network interface or the like.
[0016]
The door opening / closing mechanism 3 is a mechanism that is controlled by a door control unit 27 of the authentication device main body 2 and opens and closes a door in a security area (not shown). The door opening / closing mechanism 3 may open and close the door itself, or may be an electric lock that unlocks and locks a key installed on the door.
[0017]
Next, the operation of the entry / exit management device configured as described above will be described.
2 and 3 are flowcharts for explaining the operation of the entry / exit management device.
That is, first, the camera 11 takes an image of the person to be authenticated (step S11). Then, the image input unit 22 inputs an image captured by the camera 11 and stores the image in the image memory 23. When the image captured by the camera 11 is loaded into the image memory 23, the processing unit 21 performs a process of detecting a face image from the image stored in the image memory 23 (Step S12). The face image is detected by extracting feature points of the face such as eyes, nostrils, and lip end points from the image. Upon detecting the face image, the processing unit 21 performs a matching process between the face image detected from the captured image and the face data registered in the dictionary 28 (step S13).
[0018]
In this matching process, when face data of a plurality of persons (face data of N persons) is registered in the dictionary 28, the face image detected from the photographed image and all face data registered in the dictionary 28 are compared. Collation is performed (1: N collation). In the case of the 1: N collation, the collation result indicates whether or not the collation with the face data of the person having the maximum collation degree is determined based on whether or not the maximum collation degree (maximum collation degree) is equal to or greater than a predetermined first threshold value. Is determined. The first threshold is a threshold for determining whether or not a face image of a person to be authenticated and face data registered in a dictionary have been compared in 1: N matching.
[0019]
That is, the processing unit 21 calculates the matching degree between the face image detected from the captured image and all the face data registered in the dictionary 28, and the maximum matching degree among the calculated matching degrees is a predetermined first matching degree. It is determined whether it is equal to or more than the threshold (step S14). When it is determined that the maximum collation degree is equal to or greater than the first threshold value (step S14, YES), the processing unit 21 informs the user that the personal authentication by the face collation has succeeded by displaying the guidance on the display unit 12 or the like. A notification is sent to the person to be authenticated (step S15). The processing unit 21 opens the door using the door opening / closing mechanism 3 by the door control unit 27 together with the guidance to the effect that the personal authentication has been successful to the person to be authenticated (step S16). Thus, the person to be authenticated can enter and exit the security area inside the door.
[0020]
If it is determined that the maximum matching degree of the matching processing is smaller than the first threshold value (step S14, NO), the processing unit 21 informs the display unit 12 that personal authentication by face matching has failed. It is displayed (step S17). At this time, it is assumed that the processing unit 21 stores the collation degree calculated in the collation processing in a memory (not shown) or the like. Further, when the 1: N collation fails, the processing unit 21 guides and displays the input guidance of the personal identification information on the display unit 12 or provides voice guidance using a speaker or the like (not shown) (step). S18).
[0021]
When guiding the input guidance of the personal identification information, the processing unit 21 determines whether or not the person to be authenticated has input the personal identification information by the operation unit 13 (step S19). In this determination, for example, it is determined whether or not the personal identification information has been input, based on whether or not the personal identification information has been input within a predetermined time. Therefore, when the personal identification information is not input within the predetermined time (step S19, NO), the processing unit 21 determines that the personal authentication for the subject has failed, and ends the processing.
[0022]
If it is determined that the personal identification information has been input by the person to be authenticated (step S19, YES), the processing unit 21 searches the dictionary 28 for the face data of the person corresponding to the input personal identification information. Processing is performed (step S20). Based on the search result, the processing unit 21 determines whether or not the face data corresponding to the personal identification information input by the person to be authenticated is registered in the dictionary 28. When it is determined that the face data corresponding to the input personal identification information does not exist, the processing unit 21 determines that the personal authentication has failed by the display unit 12 or the like and updates the face data corresponding to the person. The fact that it is impossible is notified to the person to be authenticated, and the process is terminated.
[0023]
When it is determined that there is face data corresponding to the input personal identification information (step S21, YES), the processing unit 21 performs a face data update process on the personal identification information. In the face data update process, when the degree of matching with the face data corresponding to the personal identification information is equal to or greater than a predetermined second threshold, the face data is registered in the dictionary 28 using the face image captured by the camera 11. The updated face data is updated.
[0024]
That is, the processing unit 21 determines the degree of collation between the face image of the person to be authenticated and the face data corresponding to the input personal identification information (step S22). The determination of the matching degree is performed by storing the matching degree for each face data calculated in the matching processing in step S13 in a memory (not shown), and reading out the matching degree of the face data corresponding to the personal identification information. Alternatively, a new matching process may be performed between the face image of the person to be authenticated and face data corresponding to the personal identification information to calculate the matching degree.
[0025]
When the degree of matching between the face image of the person to be authenticated and the face data corresponding to the personal identification information is determined by the above determination, the processing unit 21 determines whether the degree of matching is equal to or greater than a second predetermined threshold. (Step S23). The second threshold is a threshold for determining whether to permit updating of face data. That is, if the matching degree is equal to or greater than the second threshold, the face data is updated assuming that the face matching is successful (authentication that the user is authenticated). If the matching degree is equal to or less than the second threshold, the face The face data cannot be updated because the verification has failed.
[0026]
Alternatively, only the maximum collation obtained in the collation processing in step S13 may be stored in a memory (not shown), and only the face data of the person having the maximum collation may be updated. In this case, it is determined whether or not the face data corresponding to the personal identification information is the face data having the maximum similarity, and whether to update the face data may be determined based on the determination result. . Accordingly, in this case, since only the person having the maximum matching degree in the 1: N face matching is targeted, the security performance at the time of updating can be further improved.
Alternatively, only the matching degrees that have become equal to or greater than the second threshold value in the matching processing in step S13 may be held, and face data whose matching degrees have become equal to or greater than the second threshold value may be set as an update target. . In this case, it is determined whether or not the face data corresponding to the personal identification information input by the person to be authenticated is the face data having the matching degree equal to or larger than the second threshold, and the face data is updated based on the determination result. It is sufficient to determine whether or not this is the case. Thus, in this case, the processing speed can be improved because the processing for determining whether the face data corresponding to the personal identification information is equal to or larger than the second threshold value can be easily performed.
[0027]
When it is determined that the collation degree is smaller than the second threshold value (step S23, NO), the processing unit 21 determines from the display unit 12 or the like that the face authentication has failed for the person. (Step S24), and further notifies that face data cannot be updated (step S25). In this case, the person to be authenticated operates the operation unit 13 to perform the above-described processing again, or requests the administrator of the entry / exit management apparatus to re-register the face data in the dictionary 28. Will do.
[0028]
When it is determined that the collation degree is equal to or greater than the second threshold value (step S23, YES), the processing unit 21 confirms by the display unit 12 or the like that the personal authentication by the face collation is successful. The user is notified (step S26), and the face data of the person registered in the dictionary 28 using the face image captured by the camera 11 is updated (step S27). The face data updating process is a process of calculating a feature amount of the face based on feature points extracted from the captured face image and reflecting the calculated feature amount on the face data registered in the dictionary 28.
[0029]
When the face data updating process is completed, the processing unit 21 notifies the authenticated person to the effect that the face data has been updated on the display unit 12 and the like (step S28). The processing unit 21 opens the door using the door opening / closing mechanism 3 by the door control unit 27 together with the guidance to the effect that the face data has been updated (step S29). As a result, the person to be authenticated can enter and exit the security area in the door, and can recognize that the face data in the dictionary 28 has been updated.
[0030]
That is, in the present embodiment, 1: N face matching between a captured face image and face data registered in a dictionary is performed. Here, if the 1: N face matching fails, a process (update process) of reflecting the face image of the subject who failed in the face matching on the face data in the dictionary is performed. In this update process, personal identification information such as a personal identification number, which is unique to the person, is input in order to determine whether the face data belongs to the person. On the face matching device side, when face data of the input personal identification information exists, and the matching result between the captured face image and the face data corresponding to the personal identification information in the dictionary is equal to or greater than a predetermined matching degree Then, the face data of the person is updated. That is, when personal identification information such as a personal identification number is leaked to the outside, if face data is updated only by matching the personal identification information, a problem occurs in subsequent personal authentication processing using a face image. For this reason, when updating the face data, the face data is not updated unless the degree of matching between the face image of the person who has input the personal identification information and the face data corresponding to the input personal identification information is not less than a certain level. It was made.
[0031]
As described above, in the present embodiment, the face data is updated by performing an operation of only inputting the personal identification information when the face verification of 1: N is performed and the face verification fails. . Therefore, the user can update the dictionary by inputting the personal identification information only once, and the operability is improved. Furthermore, if the operability is improved so that the face data is frequently updated by the user, the performance and accuracy of the face matching process can be stabilized. In addition, since the face matching of 1: N is performed at first, the matching target is not uniquely specified, and even a person with a similar face is less likely to be intentionally mistakenly recognized as another person.
[0032]
Furthermore, even if the individual identification information of another person is stolen after the failure of face identification by another person, the collation between the captured face image and the face data corresponding to the individual identification information is equal to or more than a certain value (second threshold). If the degree of collation is not obtained, the face data is not updated, so that the risk that face data of a registered person is updated by another person is reduced, and security can be improved.
[0033]
Also, in the present embodiment, when the personal information is input after the face verification has failed, the user is notified on the screen that the face data is to be updated by display or sound, and further, the face data update result is displayed. Is also displayed to the user on the screen or by sound. This makes it possible to deal with daily changing face images such as hairstyles, facial expressions during collation, standing positions during collation, etc., and to clearly inform the user whether or not face data has been updated. Therefore, the user's understanding of the face matching process is increased, and the performance and accuracy of the face matching process can be expected to be improved.
[0034]
【The invention's effect】
As described in detail above, according to the present invention, it is possible to simplify the operation of the user when updating face data registered in advance, improve convenience, and improve security and accuracy of personal authentication. It is possible to provide a possible personal authentication device, an entry / exit management device, a personal authentication method, and an entry / exit management method.
[Brief description of the drawings]
FIG. 1 is a diagram showing a schematic configuration of an entry / exit management device according to an embodiment of the present invention.
FIG. 2 is a flowchart for explaining an operation example of the entry / exit management device.
FIG. 3 is a flowchart for explaining an operation example of the entry / exit management device.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... User interface (I / F) unit, 2 ... Authentication machine main body, 3 ... Door opening / closing mechanism, 11 ... Camera, 12 ... Display part, 13 ... Operation part, 14 ... Lighting, 21 ... Processing part (collation means), 22 image input unit, 23 image memory, 24 display control unit, 25 operation unit interface (I / F), 26 illumination control unit, 27 door control unit, 28 dictionary

Claims (6)

In a personal authentication device that performs personal authentication using an image including at least a face,
Registration means in which face data of a person and personal identification information for identifying the person of the face data are registered,
Photographing means for photographing an image including at least the face of the subject;
Collating means for determining the degree of collation between an image including at least the face of the person to be authenticated photographed by the photographing means and face data registered in the registration means;
A first authentication unit that authenticates the person to be authenticated as a person having the maximum collation degree when the maximum collation degree among the collation degrees determined by the collation means is equal to or greater than a predetermined first threshold value; When,
Guiding means for guiding the input of personal identification information to the person to be authenticated, when a maximum matching degree among the matching degrees determined by the matching means is smaller than the first threshold value,
When the degree of matching with the face data of the person corresponding to the personal identification information input by the person to be authenticated in response to the guidance by the guidance means is equal to or greater than a predetermined second threshold smaller than the first threshold, Second authentication means for authenticating a person to be authenticated as a person specified by the personal identification information;
When the second authentication unit authenticates the person to be authenticated as a person specified by the personal identification information, the second person is registered in the registration unit using an image including at least a face photographed by the photographing unit. Updating means for updating face data corresponding to the personal identification information,
A personal authentication device comprising: Further, when the updating unit updates the face data registered in the registration unit, the notifying unit notifies the authenticated person that the face data registered in the registration unit has been updated. The personal authentication device according to claim 1, wherein: In an entry / exit management device that manages entry / exit of a person using an image including at least a face,
Registration means in which face data of a person who is permitted to pass in advance and personal identification information for identifying the person of the face data are registered,
Photographing means for photographing an image including at least a face of a passerby;
A matching unit that determines a matching degree between an image including at least a face of a passerby photographed by the photographing unit and face data registered in the registration unit;
A first traffic permitting means for permitting the passerby to pass when the maximum collation degree among the collation degrees determined by the collating means is equal to or more than a predetermined first threshold value;
A guidance unit that guides the passer-by to input the personal identification information, when the maximum collation degree among the collation degrees determined by the collation unit is smaller than the first threshold value,
If the degree of matching with the face data of the person corresponding to the personal identification information entered by the passer-by in response to the guidance by the guide means is equal to or greater than a predetermined second threshold smaller than the first threshold, Second traffic permitting means for permitting traffic of persons,
When the second traffic permitting means permits the traffic of the passer, the face data corresponding to the personal identification information registered in the registering means is registered using an image including at least a face photographed by the photographing means. Updating means for updating;
An entry / exit management device comprising: Further, when the updating means updates the face data registered in the registration means, the information processing apparatus has a notifying means for notifying the passerby that the face data registered in the registration means has been updated. The entry / exit management device according to claim 3, characterized in that: A personal authentication method used for a personal authentication device that performs personal authentication using an image including at least a face,
A photographing step of photographing an image including at least the face of the subject,
A collation step of judging the degree of collation between an image including at least the face of the person to be authenticated photographed in the photographing step and face data of a person registered in advance in correspondence with personal identification information for identifying the person in the registration means When,
A first authentication step of authenticating the person to be authenticated as a person having the maximum collation degree when the maximum collation degree among the collation degrees determined in the collation step is equal to or greater than a predetermined first threshold value; When,
A guiding step of guiding the authenticated person to input personal identification information, when the maximum matching degree among the matching degrees determined in the matching step is smaller than the first threshold value,
When the degree of matching with the face data of the person corresponding to the personal identification information input by the person to be authenticated in accordance with the guidance in the guidance step is equal to or greater than a predetermined second threshold smaller than the first threshold, A second authentication step of authenticating a person to be authenticated as a person specified by the personal identification information;
In a case where the second authentication step authenticates the person to be authenticated as a person specified by the personal identification information, the second person is registered in the registration unit using an image including at least a face photographed in the photographing step. An updating step of updating face data corresponding to the personal identification information,
A personal authentication method comprising: An entry / exit management method used in an entry / exit management device that manages entry / exit of a person using at least an image including a face,
A photographing step of photographing an image including at least a face of a passerby;
Degree of collation between the image including at least the face of the passerby photographed in this photographing process and the face data of a person who is permitted to pass and is registered in advance in the registration means corresponding to the personal identification information for specifying the person A matching step of determining
A first traffic permitting step of permitting the passerby to pass when the maximum collation degree among the collation degrees determined in the collating step is equal to or greater than a predetermined first threshold value;
A guiding step of guiding the passer-by to input the personal identification information, when the maximum matching degree among the matching degrees determined in the matching step is smaller than the first threshold value,
If the degree of matching with the face data of the person corresponding to the personal identification information input by the passer-by in accordance with the guidance in the guide step is equal to or greater than a predetermined second threshold smaller than the first threshold, A second traffic permitting step of permitting traffic of a person;
When the passerby is allowed to pass by the second pass permitting step, face data corresponding to the personal identification information registered in the registering means is registered using an image including at least a face photographed in the photographing step. An update process to update,
An entry / exit management method comprising:

Images