Information processing apparatus, face authentication system, and information processing method

Abstract

To provide an information processing device, a face authentication system, and an information processing method capable of improving a processing speed of collation using a face image of a person passing through a specific area.SOLUTION: According to an aspect of the present invention, an information processing apparatus includes: an acquisition unit configured to acquire an image of a person who can board a vehicle traveling from a first point to a second point, the person being captured at the first point, wherein the person can reach the second point by the vehicle based on information of a face image included in the image, and, the processing unit excludes a person who cannot reach the second point by the vehicle by a predetermined time from the candidates based on time information when the face image is captured and information on a theoretical moving time by the vehicle calculated based on an actual measurement value of an actual behavior of an entering person and an exiting person from the first point to the second point.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, a face authentication system, and an information processing method. [Background technology]

[0002] There is known a technology that uses facial recognition to manage the entry and exit of people passing through gates installed at stations, airports, etc. Patent Document 1 discloses a technology that enables people to pass smoothly through a gate. The technology in Patent Document 1 extracts feature amounts of an object in a captured image of the area before passing through the gate, and performs a matching determination based on pre-registered matching information (such as information related to the feature amounts of the person) and the estimated distance from the person approaching the gate to the gate. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-133364 Summary of the Invention [Problem to be solved by the invention]

[0004] Since it takes a person only a few seconds to pass through a gate, if people passing through the gate are matched (or authenticated) using facial images, the process is expected to be completed in a short time.

[0005] Non-limiting examples of the present disclosure contribute to providing an information processing device, a face recognition system, and an information processing method that can improve the processing speed of matching using facial images of people passing through a specific area such as a gate (hereinafter sometimes abbreviated as "facial image matching" or "facial image authentication"). [Means for solving the problem]

[0006] An information processing device according to one embodiment of the present disclosure includes an acquisition unit that acquires images of persons who may be boarding a vehicle traveling from a first location to a second location, the images being taken at the first location; and a processing unit that determines, based on facial image information contained in the images, candidates for persons who may be able to reach the second location by the vehicle and who will be subject to face matching at the second location. The processing unit excludes from the candidates persons who are unable to reach the second location by the vehicle by a predetermined time, based on information about the time the facial image was taken and information about the theoretical travel time by the vehicle calculated based on actual measurements of the behavior of actual entrants and exiting persons from the first location to the second location.

[0007] A facial recognition system according to one embodiment of the present disclosure includes a camera that photographs, at a first location, persons who may be boarding a vehicle traveling from the first location to a second location; and an information processing device that acquires images photographed by the camera and, based on facial image information contained in the images, determines candidates for persons who may be able to reach the second location by the vehicle and who will be the subject of facial matching at the second location.The information processing device excludes from the candidates persons who are unable to reach the second location by the vehicle by a predetermined time, based on information about the time the facial image was photographed and information about the theoretical travel time by the vehicle calculated based on actual measurements of the behavior of actual entrants and exiting persons from the first location to the second location.

[0008] An information processing method according to one embodiment of the present disclosure causes a computer to execute a program that acquires an image of a person who may be riding in a vehicle traveling from a first location to a second location, taken at the first location, and determines candidates for a person who may be able to reach the second location by the vehicle and who will be the subject of face matching at the second location, based on information about the facial image contained in the image, information about the time the facial image was taken, and information about the theoretical travel time by the vehicle from the first location to the second location calculated based on actual measurements of the behavior of actual people entering and leaving the venue.

[0009] These comprehensive or specific aspects may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a recording medium, or may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium. [Effects of the Invention]

[0010] According to an embodiment of the present disclosure, the processing speed for matching face images of people passing through a specific area can be improved.

[0011] Further advantages and benefits of an embodiment of the present disclosure will become apparent from the specification and drawings. Such advantages and / or benefits may be provided by some of the embodiments and features described in the specification and drawings, respectively, but not necessarily all of them may be provided to obtain one or more identical features. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing an overview of functions of a face authentication system according to the present disclosure. [Figure 2] FIG. 1 is a diagram showing a configuration example of a face authentication system according to a first embodiment. [Figure 3] FIG. 1 shows an example of the hardware configuration of a face recognition server and an entrance face recognition device. [Figure 4] FIG. 1 is a diagram showing an example of the functional configuration of a face authentication server and a gate according to a first embodiment. [Figure 5] 1 is a flowchart illustrating an example of the operation of the face authentication system according to the first embodiment. [Figure 6] FIG. 10 is a diagram showing an example of the functional configuration of a face authentication server and a gate according to a second embodiment. [Figure 7] 10 is a flowchart illustrating an example of the operation of a face authentication system according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functions are designated by the same reference numerals, and redundant description will be omitted.

[0014] (Embodiment 1) 1 is a diagram showing an overview of functions of a face authentication system 100 according to the present disclosure. The face authentication system 100 includes a face authentication (face search) function 100a, an entrance / exit management function 100c, and the like.

[0015] The face recognition function 100a performs face recognition by comparing the face images registered in the face registration database (DB) 100b with the face images of people passing through gates (entrance gates, exit gates, etc.) installed at facilities such as airports, stations, and event venues.

[0016] The face registration DB 100b stores information on face images captured by, for example, a smartphone, a ticket vending machine, or the like.

[0017] Matching involves comparing a registered face image with the face image of a person passing through the gate to determine whether the pre-registered face image matches the face image of the person passing through the gate, or whether the pre-registered face image and the face image of the person passing through the gate are the face images of the same person.

[0018] On the other hand, authentication is the process of proving to the outside (e.g., the gate) that the person whose facial image matches a pre-registered facial image is the person in question (in other words, that they are a person who should be allowed to pass through the gate).

[0019] However, in this disclosure, "verification" and "authentication" may be used interchangeably.

[0020] The entry / exit management function 100c acquires information related to entry / exit (such as identification information for identifying the gate through which entry / exit was made, and the time of entry / exit at the gate) from the entry / exit history information DB 100d, and controls the opening / closing operation of the opening / closing door mechanism according to the collation results.

[0021] Furthermore, the entrance / exit management function 100c transmits information about the entrance / exit record to, for example, the smartphone member service S. The information about the entrance / exit record includes, for example, the time of entry into the gate and the time of exit from the gate.

[0022] The smartphone membership service S is, for example, a service that provides an entrance / exit management system using facial recognition. A smartphone user who receives this service takes a picture of a person's face using a camera attached to the smartphone, and registers the face image for facial recognition in the face registration DB 100b. For example, this service includes a service that notifies the user of information related to gate entry / exit records.

[0023] Next, a configuration example of a face recognition system will be described with reference to Fig. 2. In the following, as an example, a case will be described in which the face recognition system is applied to entrance / exit management using face recognition at gates installed at the entrances and exits of each station on a railway network.

[0024] FIG. 2 is a diagram showing an example of the configuration of a face authentication system according to this embodiment. The face authentication system 100 according to this embodiment is, for example, a system that controls gates (such as ticket gates) installed at the entrances and exits of stations. In the face authentication system 100 according to this embodiment, for example, management of entry and exit of users who use a facility is performed by face authentication. For example, when a user passes through a gate to enter a facility (for example, a station premises), face authentication is used to determine whether the user is a person permitted to enter the facility. Also, when a user passes through a gate to leave the facility, face authentication is used to determine whether the user is a person permitted to leave the facility. Note that "face authentication" may be considered a concept included in "matching using a face image."

[0025] The facial authentication system 100 includes a gate control device 20 that controls a gate 400, and a facial authentication server 200. The facial authentication system 100 also includes a camera 1 for photographing faces, a QR Code (registered trademark) reader 2, a passage management photoelectric sensor 3, an opening / closing door mechanism 4, an entrance guide indicator 5, a passage guide LED (Light Emitting Diode) 6, and a guidance display 7. The facial authentication system 100 also includes a speaker 8, an interface board 9, an interface driver 10, a network hub 30, etc.

[0026] The gate control device 20 is connected to a network hub 30 and can communicate with a server 200 via the network hub 30 and a network 300. The server 200 performs processing related to facial authentication. Therefore, the server 200 may be referred to as a facial authentication server 200. The gate control device 20 is, for example, a device that controls gates installed in stations. The gate control device 20 controls the opening and closing door mechanism 4 of a gate 400. For example, the gate 400 is opened for people who are permitted entry through facial authentication. On the other hand, the gate is closed for people who fail facial authentication.

[0027] The gate control device 20 includes an entrance face authentication device 21a and an exit face authentication device 21b. The gate control device 20 performs gate control, including gate opening and closing operations, based on outputs from the entrance face authentication device 21a and the exit face authentication device 21b.

[0028] For facial recognition by the entrance facial recognition device 21a and the exit facial recognition device 21b, information on facial images of, for example, hundreds of thousands to tens of millions of people is used. This information is at least recorded in the face recognition server 200. Hereinafter, the information used for face recognition may be referred to as "authentication information" or "matching information." For example, the authentication information may be registered in advance in the face recognition server 200 through the usage procedure of a user who uses the entrance / exit management service using face recognition.

[0029] It should be noted that the entrance face authentication device 21a and the exit face authentication device 21b only need to be arranged so as to be able to communicate with the face authentication server 200. The entrance face authentication device 21a and the exit face authentication device 21b may be incorporated into the gate control device 20, or at least one of the entrance face authentication device 21a and the exit face authentication device 21b may be provided outside the gate control device 20. Also, while FIG. 2 shows an example in which the gate 400 serves both as an entrance and an exit, the gate 400 may be dedicated to entrance or exit. If the gate 400 is dedicated to entrance, the gate control device 20 does not need to include the exit face authentication device 21b. If the gate 400 is dedicated to exit, the gate control device 20 does not need to include the entrance face authentication device 21a.

[0030] Camera 1 is a camera for capturing an image of the face of a person passing through gate 400.

[0031] The QR code reader 2 reads a QR code that contains information that identifies a person passing through the gate. For example, among people passing through the gate, those who are subject to entrance and exit control that does not use facial recognition are authenticated by having the QR code reader 2 read their QR code.

[0032] The passage control photoelectric sensor 3 detects whether a person has entered the gate and whether a person permitted to pass through the gate has passed through the gate. For example, the passage control photoelectric sensor 3 may be installed at multiple locations, including a location that detects whether a person has entered the gate and a location that detects whether a person has passed through the gate. The passage control photoelectric sensor 3 is connected to the gate control device 20, for example, via an interface board 9. Note that the method of detecting the entry and passage of a person is not limited to the method using a photoelectric sensor, and other methods can also be used, such as monitoring the movement of a person captured by a camera installed on the ceiling, etc. In other words, the photoelectric sensor is just one example of a passage control sensor, and other sensors may also be used.

[0033] The opening and closing door mechanism 4 is connected to the gate control device 20 via, for example, an interface board 9.

[0034] The entrance guide indicator 5 notifies whether or not passage through the gate 400 is permitted. The entrance guide indicator 5 is connected to the gate control device 20 via an interface driver 10, for example.

[0035] The passage guide LED 6 emits light in a color corresponding to the state of the gate 400 to indicate whether the gate 400 is in a state where it is possible to pass through, for example.

[0036] The guidance display 7 displays, for example, information regarding whether or not passage is permitted.

[0037] The speaker 8 generates, for example, a sound indicating whether or not passage is permitted.

[0038] Next, the hardware configurations of the face authentication server 200 and the entrance face authentication device 21a will be described with reference to Fig. 3. Note that the exit face authentication device 21b has the same hardware configuration as the entrance face authentication device 21a, so a description of the hardware configuration of the exit face authentication device 21b will be omitted. Fig. 3 is a diagram showing an example of the hardware configuration of the face authentication server and the entrance face authentication device.

[0039] The face authentication server 200 includes a processor 601, a memory 602, and an input / output interface 603 used for transmitting various types of information. The processor 601 is an arithmetic device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The memory 602 is a storage device realized using a RAM (Random Access Memory), a ROM (Read Only Memory), or the like. The processor 601, the memory 602, and the input / output interface 603 are connected to a bus 604, and various types of information are exchanged via the bus 604. The processor 601 realizes the functions of the face authentication server 200 by reading, for example, programs and data stored in the ROM onto the RAM and executing processing.

[0040] The entrance face authentication device 21a includes a processor 701, a memory 702, and an input / output interface 703 used for transmitting various types of information. The processor 701 is an arithmetic device such as a CPU or a GPU. The memory 702 is a storage device realized using a RAM, a ROM, or the like. The processor 701, the memory 702, and the input / output interface 703 are connected to a bus 704, and various types of information are exchanged via the bus 704. The processor 701 realizes the functions of the entrance face authentication device 21a by reading, for example, programs, data, and the like stored in the ROM onto the RAM and executing processing.

[0041] 4 is a diagram showing an example of the functional configuration of the face authentication server and gate according to Embodiment 1. The entrance gate 400a, the exit gate 400b, and the face authentication server 200 are connected to each other via a network 300.

[0042] The entrance gate 400a is equipped with an entrance face authentication device 21a and a camera 1a.

[0043] For example, camera 1a captures an image of a person moving toward entrance gate 400a.

[0044] The entrance face authentication device 21a includes a communication unit 101a that communicates with the face authentication server 200 via the network 300, and a processing unit 102a.

[0045] The exit gate 400b is equipped with an exit face authentication device 21b and a camera 1b.

[0046] Camera 1b captures, for example, a person moving toward exit gate 400b.

[0047] The exit face authentication device 21b includes a communication unit 101b that communicates with the face authentication server 200 via the network 300, a processing unit 102b, and a buffer 103b that records various information.

[0048] The face authentication server 200 includes a communication unit 201 that communicates with the entrance face authentication device 21a and the exit face authentication device 21b via a network 300, a face registration DB 203 that manages authentication information, a processing unit 202, and an entrance visitor DB 204. The authentication information managed by the face registration DB 203 includes information on the face images of, for example, hundreds of thousands to tens of millions of users, and the authentication information managed by the entrance visitor DB 204 is only a portion of this information. The authentication information may also include information on the movement history of each registered person (entrance and exit history information). The information on the movement history may include, for example, the registrant's past entry points (e.g., stations from which they entered), the time of entry, the exit points (e.g., stations from which they exited), the time of exit, and information about the registrant's commuter pass.

[0049] 4 shows an example in which one face authentication server 200, one entrance gate 400a, and one exit gate 400b are connected to the network 300, but the present disclosure is not limited to this. For example, multiple entrance gates 400a and exit gates 400b may be connected to the network 300. For example, in the case of a railway network, the entrance gate 400a and exit gate 400b of each station may be connected to the network 300. Furthermore, one gate 400 may have the functional configuration of both the entrance face authentication device 21a and the exit face authentication device 21b shown in FIG.

[0050] Next, an example of the operation of the face authentication server 200, the entrance face authentication device 21a, and the exit face authentication device 21b according to the first embodiment will be described.

[0051] FIG. 5 is a flowchart illustrating an example of the operation of the face authentication system according to the first embodiment.

[0052] In the following, an example of operation will be described for the entry and exit of a certain user Y. In the following, entrance gate 400a refers to the gate through which user Y enters, and exit gate 400b refers to the gate through which user Y exits. In this embodiment, a railway network is used as an example for explanation, and therefore entrance gate 400a and exit gate 400b are provided at each station included in the railway network. Here, travel by train from the station where entrance gate 400a is provided to the station where exit gate 400b is provided may correspond to travel from entrance gate 400a to exit gate 400b.

[0053] First, the case where user Y enters through entrance gate 400a will be described.

[0054] A user Y enters the entrance gate 400a (S100). The entrance of the user Y to the entrance gate 400a may be detected by the passage management photoelectric sensor 3, for example.

[0055] The camera 1a at the entrance gate 400a captures an image of an area including the face of the user Y, and the processing unit 102a of the entrance face authentication device 21a detects the face area (captured face image) from the image captured by the camera 1a (S101).

[0056] The processing unit 102a transmits a request for face search to the face authentication server 200 via the communication unit 101a (S102). The request for face search may include a captured face image.

[0057] The processing unit 202 of the face authentication server 200 receives the request for face search via the communication unit 201 (S103).

[0058] The processing unit 202 of the face authentication server 200 executes a face search (S104). For example, the processing unit 202 executes a face search based on a score indicating the likelihood that two face images belong to the same person. For example, the processing unit 202 calculates a score between a face image (candidate face image) in the authentication information of each registrant contained in the face registration DB 203 and a photographed face image of user Y, and determines that user Y corresponds to the person of the candidate face image with the highest score. Then, based on the determined information of user Y, the processing unit 202 determines whether user Y is a person permitted to pass through the entrance gate 400.

[0059] The communication unit 201 transmits the search result including the determination result in S104 to the entrance face authentication device 21a (S105).

[0060] The processing unit 102a of the entrance face authentication device 21a receives the search result via the communication unit 101a (S106). Based on the received search result, the processing unit 102a determines whether or not to permit the passage of user Y (S107).

[0061] If passage is permitted (Yes in S107), the entrance gate 400a opens the door and notifies the user Y of information indicating permission to pass (S108a). For example, permission to pass may be notified to the user Y by displaying an indicator and / or by audio notification.

[0062] If passage is not permitted (No in S107), the entrance gate 400a keeps the door closed and notifies information indicating that passage is not permitted (S108b). Then, the process of S101 is executed.

[0063] The processing unit 102a detects the passage of user Y and transmits a request to register that user Y has passed through the entrance gate 400a via the communication unit 101a (S109). The registration request to register that user Y has passed through the entrance gate 400a may include the identification (ID) of the user who passed through, the time of passage, and information about the station or gate that was passed through.

[0064] The processing unit 202 of the face authentication server 200 receives the passage completion registration request from user Y via the communication unit 201 (S110).

[0065] The processing unit 202 of the face authentication server 200 executes an entry completion process for user Y (S111). For example, the processing unit 202 extracts authentication information of user Y from the face registration DB 203 and stores it in the visitor DB 204. The authentication information stored in the visitor DB 204 is authentication information of a person who has completed entry among registered persons (hereinafter, may be referred to as an "enterer"). The visitor is an example of an exit candidate who will exit through the exit gate 400b. The exit candidate is an example of a person who can reach the exit gate 400b and is an example of a candidate for a person who will be subject to face matching at the exit gate 400b. For example, in the case of a railway network, the visitor is an example of a person who may board (or board) a train (an example of a vehicle) traveling from an entrance gate 400a (a first point) of a certain station to an exit gate 400b (a second point) of another station. Note that the station from which the visitor entered and the station from which the visitor exits may be the same.

[0066] In the following, storing the authentication information of a visitor in visitor DB204 may be described as generating (creating) visitor DB204. Similarly, for other DBs described below, storing information in a DB may be described as generating (creating) a DB. Furthermore, using information stored in a DB may be abbreviated to using a DB. Furthermore, sending (or receiving) information stored in a DB may be abbreviated to sending (or receiving) a DB. In other words, a "DB" may be interpreted as a physical or virtual component that stores information (or data), or as the stored information (or data).

[0067] The visitor DB 204 stores authentication information of visitors entering through the entrance gate 400a of each station on the railway network.

[0068] Then, at the entrance gate 400a, the processes from S101 onwards are executed for users who enter the entrance gate 400a after user Y.

[0069] Next, the case where user Y exits through the exit gate 400b will be described.

[0070] The user Y enters the exit gate 400b (S160). The entry of the user Y into the exit gate 400b may be detected by the passage management photoelectric sensor 3, for example.

[0071] The camera 1b at the exit gate 400b captures an image of an area including the face of the user Y, and the processing unit 102b of the exit face authentication device 21b detects a captured face image from the image captured by the camera 1b (S161).

[0072] The processing unit 102b transmits a request for face search to the face authentication server 200 via the communication unit 101b (S162). The request for face search may include the captured face image.

[0073] The processing unit 202 of the face authentication server 200 receives the request for face search via the communication unit 201 (S163).

[0074] The processing unit 202 of the face authentication server 200 executes a face search (S164). For example, the processing unit 202 calculates a score between the candidate face image of the authentication information of each visitor included in the visitor DB 204 and the photographed face image of user Y, and determines that user Y corresponds to the person of the candidate face image that showed the highest score. Then, based on the determined information of user Y, the processing unit 202 determines whether user Y is a person permitted to pass through the exit gate 400b.

[0075] The processing unit 202 transmits the search result including the determination result in S164 to the exiting face authentication device 21b (S165).

[0076] The processing unit 102b of the exit face authentication device 21b receives the search result via the communication unit 101b (S166). Based on the received search result, the processing unit 102b determines whether or not to permit the passage of user Y (S167).

[0077] If passage is permitted (Yes in S167), the exit gate 400b opens the door and notifies information indicating that passage is permitted (S168a).

[0078] If passage is not permitted (No in S167), the exit gate 400b keeps the door closed and notifies information indicating that passage is not permitted (S168b). Then, the process of S161 is executed.

[0079] The processing unit 102b detects the passage of user Y and transmits a request to register that user Y has passed through the exit gate 400b via the communication unit 101b (S169). The registration request to register that user Y has passed through the exit gate 400b may include the identification (ID) of the user who passed through, the time of passage, and information about the station or gate that was passed through.

[0080] The processing unit 202 of the face authentication server 200 receives the passage completion registration request from user Y via the communication unit 201 (S170).

[0081] The processing unit 202 executes an exit completion process for user Y (S171). For example, the processing unit 202 executes a deletion process for deleting the authentication information of user Y from the visitor DB 204.

[0082] Then, at the exit gate 400b, the processes from S161 onwards are executed for the users who enter the exit gate 400b after user Y.

[0083] With this processing, the facial search for users passing through exit gate 400b can target information about people who entered through entrance gate 400a from among the authentication information, thereby speeding up the facial recognition processing. In other words, since the scope of the facial search for users passing through exit gate 400b can be narrowed down to the authentication information managed by visitor DB 204, the facial recognition processing can be speeded up compared to when the scope of the facial search is limited to the authentication information managed by face registration DB 203.

[0084] 5 illustrates an example in which authentication information of a visitor (e.g., the above-mentioned user Y) is stored in the visitor DB 204 in the entry completion process (S111 in FIG. 5), but the present disclosure is not limited to this. For example, in the entry completion process, the processing unit 202 may set a flag indicating entry in the authentication information of user Y in the face registration DB 203. In this case, in face search (S163 in FIG. 5) in response to a face search request from the processing unit 102b, the processing unit 202 may calculate a score between the candidate face image of each registered person for whom a flag indicating entry is set in the authentication information in the face registration DB 203 and the captured face image of user Y. In other words, a collection of authentication information in the face registration DB 203 for which a flag is set may be treated as a virtual visitor DB 204. The processing unit 202 may then determine that user Y corresponds to the person corresponding to the candidate face image with the highest score. In this case, the processing unit 202 may cancel (delete) the entry flag set in the authentication information of the user Y in the face registration DB 203 in the exit completion process (S171 in FIG. 5).

[0085] As described above, in the first embodiment, the communication unit 201 of the face authentication server 200 (an example of an information processing device) acquires an image taken at the entrance gate 400a of a person who may board a train (an example of a vehicle) traveling from the entrance gate 400a (an example of a first location) to the exit gate 400b (an example of a second location). The processing unit 202 determines candidates for people (e.g., entrants) who may reach the exit gate 400b by train, based on facial image information included in the image taken at the entrance gate 400a. With this configuration, the face search at the exit gate 400b can target people who have entered through the entrance gate 400a, thereby improving the processing speed of matching facial images of people passing through a specific area such as a gate.

[0086] Furthermore, in this embodiment 1, authentication at the entrance gate 400a and authentication at the exit gate 400b are performed using facial images, which makes it easier to prevent unauthorized entry and exit (e.g., impersonation) compared to using a medium that makes it difficult to identify the wearer, such as an IC card, and improves security in entrance and exit management.

[0087] In the first embodiment described above, the face authentication server 200 includes the visitor DB 204. However, the present disclosure is not limited to this. For example, the visitor DB may be provided at the exit gate 400b of each station. In this case, the face authentication server 200 may generate visitor information by extracting the visitor's authentication information from the face registration DB 203 and distribute the visitor information to each station. In this case, the exit face authentication device 21b at the exit gate 400b may store the distributed visitor information in the visitor DB. In this case, the processing unit 102b of the exit face authentication device 21b may calculate a score between the candidate face image of each visitor included in the visitor DB and the photographed face image, and determine that the person in the photographed face image corresponds to the person in the candidate face image with the highest score. In this way, the matching of the faces of departing people can be completed at the exit gate 400b, thereby further increasing the processing speed. In this case, each exit gate 400b may share information on exiting persons with the face authentication server 200, thereby reflecting the cancellation process in the visitor DB 204.

[0088] Furthermore, in the first embodiment described above, a device may be present that relays communication between the facial authentication server 200 and the entrance gate 400a or the exit gate 400b. For example, a relay server that coordinates communication between the entrance gate 400a and the exit gate 400b may be installed at each station, and communication to the network 300 may be performed via the relay server. In this case, the information in the visitor DB 204 described above may be distributed from the facial authentication server 200 to the relay server and stored by the relay server. In other words, the relay server may have the visitor DB 204 described above. By having the relay server perform facial authentication using this visitor DB 204, processing results such as the debiting of exiting persons can be easily synchronized between each of the exit gates 400b under the relay server. Furthermore, in this case, the exit gate 400b does not need to request the remote facial authentication server 200 to perform facial matching for each exiting person, which is expected to speed up the facial authentication process. In this case, in order to reflect the results of the cancellation process in one relay server in the visitor DB of another relay server, a process may be performed to periodically synchronize the visitor DBs between the face authentication server 200 and the relay servers.

[0089] Furthermore, in the above-described first embodiment, an example has been described in which the authentication information of the visitor contained in the visitor DB 204 is used for facial recognition at the exit gate 400b, but the present disclosure is not limited to this. For example, the authentication information of the visitor may be used to detect suspicious persons, lost children, sick persons, etc. For example, if the authentication information of visitor Z remains in the visitor DB 204 for a certain period of time (e.g., one day), the processing unit 202 of the face recognition server 200 determines that visitor Z has not left the premises for the certain period of time. In this case, the processing unit 202 may determine that visitor Z is a suspicious person, lost child, or sick person, and may issue a warning to staff at each station. The method of issuing the warning is not particularly limited, and, for example, information indicating the warning may be notified to an information terminal held by a staff member at each station, or information indicating the warning may be notified on an electronic bulletin board at each station. Furthermore, information such as age may be used as authentication information for visitor Z, or age estimation may be performed from facial information, and visitor Z may be distinguished and determined as a suspicious person, lost child, or sick person depending on their age. For example, it may be estimated that if visitor Z is a child, there is a high possibility that he or she is lost, if visitor Z is elderly, there is a high possibility that he or she is sick, and if visitor Z is of any other age, there is a high possibility that he or she is suspicious. In this case, the warning method may be changed depending on the determination result. For example, information about visitor Z who is likely to be lost may be widely announced on an electronic bulletin board, information about visitor Z who is likely to be sick may be notified to the first aid room, and information about visitor Z who is likely to be suspicious may be notified to security guards.

[0090] (Embodiment 2) In the second embodiment, an example will be described in which the visitors are further narrowed down based on the movement range of the visitors who entered from a certain point. In the second embodiment below, an example will be described in which the movement range of the visitors who entered from a certain station is used.

[0091] Fig. 6 is a diagram showing an example of the functional configuration of a face authentication server and a gate according to the embodiment 2. In Fig. 6, the same components as those in Fig. 4 are denoted by the same reference numerals, and the description thereof may be omitted.

[0092] 6 includes a communication unit 201 that communicates with the entrance face authentication device 21a and the exit face authentication device 21b via the network 300, a face registration DB 203 that manages authentication information, a processing unit 202, a movement range estimation processing unit 801, a movement time DB 802, and an exit candidate DB 803. The processing unit 202 and the movement range estimation processing unit 801 may be collectively referred to as the "processing unit."

[0093] The movement range estimation processing unit 801 performs processing to estimate the movement range of a visitor based on the visitor's authentication information contained in the visitor DB 204 and information related to travel time stored in the travel time DB 802. The movement range estimation processing unit 801 generates information (exit candidate information) related to exit candidates who may exit from the exit gate 400b based on the estimation result, and stores the information in the exit candidate DB 803. The exit candidate information may be generated for each exit gate 400b (for example, for each station). Furthermore, the exit candidate information associated with the station may be stored in the exit candidate DB 803. Hereinafter, the exit candidate information associated with station A may be abbreviated as the exit candidate information of station A. The exit candidate information of station A is information related to candidates who may exit from the exit gate 400b provided at station A. In other words, the exit candidates for Station A correspond to people who are entrants and who are not able to exit Station A (people who are not able to reach the exit gate 400b of Station A).

[0094] For example, the movement range estimation processing unit 801 estimates the movement range of a visitor based on the station from which the visitor entered (entry station), the time at which the visitor entered, the theoretical travel time between stations, and the time at which the exit candidate information is generated (e.g., the current time). The time at which the visitor entered may be, for example, the time at which the visitor was photographed by camera 1a at entrance gate 400a. The station from which the visitor entered (entry station) and the time at which the visitor entered may be stored in the visitor DB 204 in association with the visitor's authentication information. The movement range estimation processing unit 801 may also estimate the movement range of a visitor at predetermined intervals and generate (update) the exit candidate information.

[0095] The theoretical travel time between stations may be, for example, the shortest travel time between stations, or the shortest travel time plus a margin based on train operation information, etc. For example, the shortest travel time between Station A and Station B is the shortest time from the time of entering through the entrance gate 400a of Station A to the time of exiting through the exit gate of Station B. For example, the shortest travel time may include the time required to travel within the station premises.

[0096] The theoretical travel time may be determined based on, for example, the distance between stations and / or the timetable of the rail network that includes the stations, e.g., the timetable indicating the scheduled operation of trains traveling on the rail network, including the times when the trains arrive at and depart from the stations.

[0097] Furthermore, the theoretical travel time may be dynamically changed (corrected) based on information on the operational status, such as train delays and cancellations, etc. This correction may be a correction of the shortest travel time itself or a correction of the margin.

[0098] The following describes an example of the estimation of the movement range in the movement range estimation processing unit 801 and the exiting candidate information.

[0099] As an example, consider a railway network with three stations, Station A, Station B, and Station C, where the shortest travel time between Station A and Station B is 10 minutes, the shortest travel time between Station A and Station C is 20 minutes, and the shortest travel time between Station B and Station C is 15 minutes.

[0100] In this example, if visitor X enters from station A at 9:00 AM, the earliest time that visitor X can exit from station B is 9:10 AM, and the earliest time that visitor X can exit from station C is 9:20 AM. In this case, it is estimated that visitor X's range of movement (e.g., stations from which he or she can exit) changes at the borders of 9:10 AM and 9:20 AM.

[0101] For example, since visitor X cannot exit from stations B and C before 9:10 a.m., the exit candidate information for stations B and C does not include visitor X's authentication information between 9:00 a.m. and before 9:10 a.m.

[0102] If the time is after 9:10 AM, visitor X can exit from station B, so the exit candidate information for station B includes the authentication information of visitor X. Note that even if the time is after 9:10 AM, visitor X cannot exit from station C before 9:20 AM, so the exit candidate information for station C does not include the authentication information of visitor X.

[0103] If the time is after 9:20 AM, visitor X can exit from stations B and C, so the exit candidate information for stations B and C includes the authentication information of visitor X. However, if visitor X exits from station B before 9:20 AM, a deletion process is performed on visitor X's authentication information, so even if the time is after 9:20 AM, the exit candidate information for stations B and C does not need to include visitor X's authentication information.

[0104] As described above, whether or not entrant X's authentication information is included in the exit candidate information for each station (e.g., Station B or Station C) is determined by the time entrant X enters from Station A, the travel time between Station A and each station, and the time at which the exit candidate information is determined (e.g., the current time).

[0105] If visitor X enters at 9:00 AM, the exit candidate information for station A after 9:00 AM may include visitor X's authentication information.

[0106] Next, in the example of the railway network described above, the relationship between the exit candidate information of station A and the time, and the relationship between the exit candidate information distributed to station B and the time will be described.

[0107] For example, if the current time is 9:10 AM, the people who are eligible to exit from Station A are visitor b1, who entered from Station B before 9:00 AM, which is the current time minus 10 minutes, and visitor c1, who entered from Station C before 8:50 AM, which is the current time minus 20 minutes. The exit candidate information for Station A generated at 9:10 AM may include the authentication information of visitor b1 and visitor c1. In this case, the authentication information of visitor b2, who entered from Station B after 9:00 AM, and visitor c2, who entered from Station C after 8:50 AM, is not included in the exit candidate information for Station A at 9:10 AM.

[0108] Also, for example, if the current time is 9:10 AM, the people who are eligible to exit from Station B are entrant a3, who entered from Station A before 9:00 AM, which is 10 minutes after the current time, and entrant c3, who entered from Station C before 8:55 AM, which is 15 minutes after the current time. The exit candidate information for Station B at 9:10 AM includes the authentication information of entrant a3 and entrant c3. In this case, the authentication information of entrant a4, who entered from Station A after 9:00 AM, and entrant c4, who entered from Station C after 8:55 AM, is not included in the exit candidate information for Station B at 9:10 AM.

[0109] In this way, the movement range estimation processing unit 801 determines the exit candidate information for each station based on the entry time of the entrant, the station from which the entrant entered, the theoretical travel time between stations (e.g., the shortest travel time), and the time at which the exit candidate information is generated (updated) (e.g., the current time).

[0110] For example, if the first time obtained by subtracting the theoretical travel time from the current time is after the second time at which a certain visitor entered, the movement range estimation processing unit 801 determines the authentication information (e.g., facial image) of the certain visitor who entered at the second time as the exit candidate information.

[0111] The movement range estimation processing unit 801 may use the scheduled time for facial recognition at the exit gate 400b instead of the current time. For example, the movement range estimation processing unit 801 may estimate, at the current time, the movement range for a scheduled time for facial recognition after the current time, and generate exit candidate information for each station. For example, in an environment where a train is expected to arrive at a known scheduled arrival time and many people are expected to get off the train, the movement range estimation processing unit 801 may set a scheduled time for facial recognition based on the known scheduled arrival time and estimate the movement range using the set scheduled time. More specifically, if it is known that a train will not arrive for 10 minutes from the current time, the movement range estimation processing unit 801 may use the time 10 minutes after the current time as the scheduled time for facial recognition. For example, if the current time is used, processing that would not be performed until 10 minutes later can be started in advance. This allows the movement range estimation processing to start earlier, thereby speeding up the processing. Furthermore, for example, information regarding the scheduled time when face authentication will be performed in the exit face authentication device 21b may be acquired from the exit face authentication device 21b.

[0112] Note that the exit candidate DB803 does not include information on people who have not entered at a certain time Tn (for example, the current time) but will enter after time Tn, and therefore the later the time used as the scheduled time for facial authentication is from time Tn, the more likely it is that the most recent entrant will be omitted from the exit candidate DB803. For example, if the movement range estimation processing unit 801 sets the scheduled time for facial authentication to a time one hour after time Tn and creates the exit candidate DB803 using the set scheduled time, information on people who have not yet entered at time Tn but will enter within one hour of time Tn will not be included in the visitor DB204. Therefore, the exit candidate DB803, which is created based on the information included in the visitor DB204, does not include information on people who will enter within one hour of time Tn.

[0113] Therefore, in a configuration in which the movement range estimation processing unit 801 uses the scheduled time (hereinafter, time Tx) for performing face authentication, it may further perform a supplementary process on the exit candidate DB 803 created at time Tn, which is prior to time Tx. For example, when the current time changes from time Tn to time Tx, the movement range estimation processing unit 801 may estimate the movement range by narrowing it down to entrants who entered between time Tn and time Tx, and determine the exit candidate information to be supplemented. Then, the movement range estimation processing unit 801 may add (supplement) the exit candidate information determined at time Tx to the exit candidate DB 803 created at time Tn. In this way, although a procedure of generating the exit candidate DB 803 multiple times occurs, it is possible to narrow the range of entrants to be checked for creating the exit candidate DB 803 to be supplemented at the current time (the above-mentioned time Tx), thereby significantly shortening the processing time to be performed at the current time.

[0114] In the above example, a supplementary process may be performed for an exiting person who exited through the exit gate 400b between time Tn and time Tx. For example, when the current time changes from time Tn to time Tx, a supplementary process may be performed to delete an exiting person who exited through the exit gate 400b between time Tn and time Tx from the exit candidate DB 803 created at time Tn. The supplementary process to delete an exiting person does not have to be performed.

[0115] In the above example, the interpolation process is described when the movement range estimation processing unit 801 uses the scheduled time for performing face authentication at the exit gate 400b instead of the current time. However, the present disclosure is not limited to this. For example, when the movement range estimation processing unit 801 estimates the movement range at the current time and generates the exit candidate DB 803, instead of recreating the exit candidate DB 803, the movement range estimation processing unit 801 may perform interpolation process on the exit candidate DB 803 created one time earlier.

[0116] Next, the operations of the face authentication server 800, the entrance face authentication device 21a, and the exit face authentication device 21b according to the second embodiment will be described.

[0117] Fig. 7 is a flowchart for explaining an example of the operation of the face authentication system according to the second embodiment. Like Fig. 5, Fig. 7 explains an example of the operation when a certain user Y enters and leaves a facility. In Fig. 7, the same processes as those in Fig. 5 are denoted by the same reference numerals, and explanations thereof will be omitted.

[0118] In the flowchart of FIG. 7, a movement range estimation process is added.

[0119] The movement range estimation processing unit 801 of the face authentication server 800 performs movement range estimation processing (S201). The movement range estimation processing unit 801 stores the exit candidate information for each station in the exit candidate DB 803. The exit candidate DB 803 is used when the processing unit 202 of the face authentication server 800 receives a face search request from the exit gate 400b.

[0120] The processing unit 102b transmits a request for face search to the face authentication server 800 via the communication unit 101b (S162). The request for face search may include a captured face image.

[0121] The processing unit 202 of the face authentication server 800 receives the face search request from the exit gate 400b via the communication unit 201 (S163).

[0122] The processing unit 202 of the face authentication server 800 executes a face search (S202). For example, the processing unit 202 calculates a score between the facial image of each exit candidate included in the exit candidate DB 803 of the station equipped with the exit gate 400b and the photographed facial image of user Y, and determines that user Y corresponds to the exit candidate whose facial image shows the highest score. Then, based on the determined information of user Y, the processing unit 202 determines whether user Y is a person permitted to pass through the exit gate 400b.

[0123] The processing unit 202 transmits the search result including the determination result in S202 to the exiting face authentication device 21b (S165).

[0124] The processing unit 202 of the face authentication server 800 receives the passage completion registration request from user Y via the communication unit 201 (S170).

[0125] The processing unit 202 executes an exit completion process for user Y (S171). For example, the processing unit 202 executes a deletion process for deleting the authentication information of user Y from the visitor DB 204.

[0126] As described above, the movement range estimation process is executed based on the authentication information included in the visitor DB 204. Therefore, in the movement range estimation process executed after the authentication information of user Y is deleted from the visitor DB 204, the authentication information of user Y is not included in the exit candidate information of each station. By deleting a person who has passed through the exit gate 400b of a certain station and completed their exit (hereinafter, may be referred to as an "exiting person") from the visitor DB 204, the face recognition server 800 can exclude the exiting person from the exit candidate information of stations from which the exiting person actually exited and stations from which the exiting person did not exit.

[0127] As described above, in the second embodiment, face search at exit gate 400b can target people who have entered through entrance gate 400a and are capable of reaching exit gate 400b (people who can exit through exit gate 400b), thereby improving the processing speed of face image matching of people passing through a specific area such as a gate. In other words, according to the second embodiment, in face search at exit gate 400b, people who are not capable of reaching exit gate 400b can be excluded from the search targets.

[0128] In the second embodiment described above, the facial recognition server 800 includes the exit candidate DB 803 for each station. However, the present disclosure is not limited to this. For example, the exit candidate DB may be provided at the exit gate 400b of each station. In this case, the facial recognition server 800 may generate exit candidate information for each station and distribute the exit candidate information for each station. In this case, the exit face recognition device 21b at the exit gate 400b may store the distributed exit candidate information in the exit candidate DB. In this case, the process 102b of the exit face recognition device 21b may calculate a score between the candidate face image of each exit candidate included in the exit candidate DB and the photographed face image, and determine that the person in the photographed face image corresponds to the exit candidate with the face image that has the highest score. In this way, the matching of the faces of the exiting persons can be completed at the exit gate 400b, thereby further increasing the processing speed. In this case, each exit gate 400b may share information about exiting persons with the facial recognition server 800, thereby reflecting the cancellation process in the entrance person DB 204. Note that the exiting person information may be shared between each exit gate 400b, and the process of reflecting the cancellation process in the exit candidate DB may or may not be performed. This is because the exit candidate DB is remade as needed based on the entrance person DB 204, and so if the exit candidate DB is updated frequently enough, the cancellation process reflected in the entrance person DB 204 will ultimately be reflected in the exit candidate DB as well.

[0129] Furthermore, in the second embodiment described above, a device may be present that relays communication between the facial authentication server 800 and the entrance gate 400a or the exit gate 400b. For example, a relay server that coordinates communication between the entrance gate 400a and the exit gate 400b may be installed at each station, and communication to the network 300 may be performed via the relay server. In this case, the information in the visitor DB 204 described above may be distributed to the relay server. This facilitates synchronization of the exit process between each of the exit gates 400b under the relay server. Furthermore, in this case, the exit gate 400b does not need to request a remote facial authentication server 800 to perform face matching for each exiting person, which is expected to speed up the facial authentication process. Furthermore, in this case, the visitor DBs may be periodically synchronized between the facial authentication server 800 and the relay server to reflect the cancellation process performed at the exit gate 400b under the relay server. For the same reason as above, the process of reflecting the cancellation process in the exit candidate DB held by each relay server may or may not be performed.

[0130] Furthermore, if the exit candidate DB is provided at the exit gate 400b, the facial recognition server 800 may set a margin based on feedback information from the exit face recognition device 21b at the exit gate 400b. The facial recognition server 800 may then generate exit candidate information based on a theoretical travel time that includes the set margin. For example, the feedback information may include information regarding the capacity of the exit candidate DB at the exit gate 400b and / or information regarding matching errors at the exit gate 400b. The facial recognition server 800 may dynamically set the margin for each station based on the feedback information. Generally, the larger the margin, the larger the size of the exit candidate DB. However, since the amount of facial information to be matched increases, facial matching failures become less likely. Therefore, for example, if the capacity of the buffer 103b is small, the margin may be reduced to reduce the size of the exit candidate DB. Furthermore, the accuracy of facial matching may be improved by increasing the margin as the number of facial recognition failures increases.

[0131] Furthermore, in the above-described second embodiment, an example has been described in which the authentication information of the exit candidate stored in the exit candidate DB 803 is used for facial recognition at the exit gate 400b, but the present disclosure is not limited thereto. For example, the authentication information of the exit candidate may be used to detect a suspicious person, a lost child, a sick person, or the like. For example, if the authentication information of the exit candidate Z remains in the exit candidate DB 803 for a certain period (e.g., one day), the processing unit 202 of the face recognition server 800 determines that the exit candidate Z has not exited for the certain period. In this case, the processing unit 202 may determine that the exit candidate Z is a suspicious person, a lost child, or a sick person, and may issue a warning to a station attendant. The method of issuing the warning is not particularly limited, and may, for example, be to notify an information terminal held by a station attendant or to notify an electronic bulletin board at each station of the warning. Furthermore, information such as age may also be used as authentication information for visitor Z, or age estimation may be performed from facial information, and visitor Z may be distinguished and judged as suspicious, lost, or sick depending on his or her age. For example, it may be estimated that if visitor Z is a child, he or she is likely to be lost, if visitor Z is elderly, he or she is likely to be sick, and if visitor Z is of any other age, he or she is likely to be suspicious. In this case, the warning method may be changed depending on the judgment result. For example, information about lost visitor Z may be widely announced on an electronic bulletin board, information about sick visitor Z may be notified to the first aid room, and information about suspicious visitor Z may be notified to security guards.

[0132] Furthermore, in the above-described second embodiment, the search ranking of exit candidates in the exit candidate information may be changed. For example, if the shortest travel time between Station A and Station B is 10 minutes, it may be assumed that visitor X, who entered from Station A, is most likely to exit from Station B at time T1, which is the entry time plus a margin of 10 minutes. In this case, as time passes from time T1, the likelihood of visitor X exiting from Station B decreases, so the search ranking of visitor X in the exit candidate information for Station B may be lowered. Furthermore, if an extremely long time has passed since time T1, visitor X may be deleted from the visitor DB 204 or the exit candidate DB 803. In current entrance and exit management using transportation IC cards, there are cases where exit is denied if more than five to six hours have passed since entry. In this second embodiment, similar processing can be achieved by deleting visitor X from the visitor DB 204 or the exit candidate DB 803.

[0133] Furthermore, in the second embodiment described above, information different from the above example may be used to estimate the visitor's movement range. For example, the visitor's station usage frequency and / or the visitor's commuter pass information may be used to estimate the visitor's movement range. The visitor's station usage frequency and / or the visitor's commuter pass information corresponds to, for example, the frequency of travel from a certain entry station to a certain exit station. For example, if visitor X exits from station B more frequently than from stations other than station B, the authentication information of visitor X may be set relatively higher for face search in the exit candidate information for station B. In this case, the authentication information of visitor X may be set relatively lower for face search in the exit candidate information for stations other than station B. By setting a ranking according to frequency of use, etc. in the exit candidate information, visitor with a high usage frequency is set as a search target earlier in the face search process, thereby speeding up the face search process.

[0134] Furthermore, in the above-described second embodiment, an example was described in which the theoretical travel time between stations was used to estimate the movement range of visitors. However, a margin for each user may be added to the theoretical travel time between stations. For example, the user's stay time within the station may be added to the margin. Furthermore, at least one of the theoretical travel time and the margin may be set based on actual measurements of the behavior of actual visitors and exiting visitors. The difference between the time listed in a train or other timetable and the actual time of entry and exit can be measured from the difference between the time when the visitor passes through the entrance gate and the time when the visitor passes through the exit gate.

[0135] Furthermore, at least one of the theoretical travel time and the margin may have a different value for each time period. For example, since train stations are expected to be more crowded during rush hour compared to other time periods, setting at least one of the theoretical travel time and the margin longer than during other time periods is likely to match the actual usage environment.

[0136] In each of the above embodiments, the information used for face search and face recognition, and the information transmitted and received between devices, may be a face image itself or features extracted from a face image. Examples of features include the distribution of face color, shape, and brightness. Features generated by more complex processing used in the field of machine learning may also be used. By using features, the size of information exchanged between the face recognition server and the exit face recognition device can be reduced. Furthermore, depending on the features used, the influence of parameters that are prone to change in the real environment can be reduced, enabling robust face recognition.

[0137] Although the above embodiments have been described using a railway network as an example, the present disclosure is not limited thereto. For example, the present disclosure may be applied to transportation such as route buses, ships, and airlines.

[0138] The present disclosure may also be applied to access control for facilities such as buildings and shopping malls that have multiple entrances and exits. The multiple entrances and exits may include, for example, a gate (e.g., a main gate) that controls access to the facility and a gate that controls access to specific rooms within the facility.

[0139] In this case, for example, the authentication information of a user who enters through a certain entrance gate within a facility is stored in the visitor DB. In this case, the authentication information in the visitor DB is used in face matching when the user exits through a certain exit gate within the facility. The face search for a user passing through the exit gate can target the information of the person who entered through the entrance gate within the authentication information, thereby speeding up the face recognition process.

[0140] For example, according to the present disclosure, it is possible to speed up face recognition processing in managing entry and exit of a building user who has left a specific room in the building until the user exits the building.

[0141] Furthermore, while the above-described embodiments are intended to perform facial authentication of people exiting a venue, the present disclosure is not limited thereto. A similar concept can be applied to facial authentication at the time of entry into a partial area when a visitor who has entered a specific area attempts to enter a partial area within the specific area that can be used by only a portion of the visitors. Specifically, the facial authentication process can be speeded up in the management of a user who has entered the building (an example of a specific area) after passing through the main gate until the user arrives at a specific floor or a specific room (for example, an office or conference room used by the user) (an example of a partial area).

[0142] Furthermore, when the present disclosure is applied to facilities such as buildings and shopping malls with multiple entrances, visitors may be further narrowed down based on the range of movement of visitors within the facility, as in the above-described embodiment 2. In this case, information equivalent to the exit candidate DB (for example, information on candidates entering a partial area) may be used not only to narrow down visitors leaving the facility, but also to narrow down visitors attempting to enter a partial area within the facility.

[0143] In addition, in each of the above embodiments, the cancellation process is performed when the passage of a user is detected, but this is not limited to this. If the passage management photoelectric sensor 3 or other passage detection device is not installed, the cancellation process may be performed when the user's face is successfully matched.

[0144] Furthermore, in each of the above embodiments, the visitor DB is created by extracting visitor authentication information from the face registration DB, but this is not limited to this. If the purpose is to manage whether or not a visitor has reliably exited the venue, face image information extracted from an image taken at the time of entry may be directly registered in the visitor DB. In this case, if there is no need to authenticate a visitor at the time of entry, the face registration DB itself may be omitted.

[0145] Furthermore, in the above-described embodiments, if facial authentication of an exiting person is unsuccessful using the entrance DB or the exit candidate DB, the person is simply prevented from passing through. However, this is not limited to this. For example, additional facial matching may be performed using a face registration DB. This allows additional facial matching to be performed even if creation of the entrance DB or the exit candidate DB has failed. Note that, although face matching using a face registration DB takes time, since the face registration DB is rarely used in this modified example, face matching is faster on average than when face matching is performed using the face registration DB every time.

[0146] Furthermore, in each of the above embodiments, the type of information stored in the entry candidate DB or the exit candidate DB may be different from the type of information used to obtain the matching results. For example, facial contour features may be used to create each DB, and facial feature features may be used to obtain the matching results. By using different information to narrow down the search and obtain the matching results, improved accuracy can be expected.

[0147] On the other hand, the same information may be used to create each DB and to obtain the matching results. In this way, evaluation is performed from the same perspective in the narrowing down and face recognition processes, which can reduce discrepancies in the judgment results. As a result, the frequency of requests to the face recognition server due to face recognition failures can be reduced, which is expected to speed up face recognition processing.

[0148] Furthermore, in the above-described embodiments, the facial images contained in the visitor DB or the exit candidate DB may not be the images themselves, but may be their features. The term "facial image information" is a concept that includes both the facial images themselves and the features of the facial images. In particular, in a configuration in which the visitor DB or the exit candidate DB is transmitted from the face recognition server to the exit face recognition device, a database consisting of features can reduce communication volume. However, in situations where the size of the visitor DB or the exit candidate DB does not significantly affect communication volume, such as when facial matching of exiting persons is performed within the face recognition server, the facial images themselves may be used as the visitor DB or the exit candidate DB.

[0149] Furthermore, in each of the above embodiments, the gate 400 is equipped with an opening / closing door mechanism 4, but the means (restriction unit) for restricting a person's movement when face matching fails is not limited to this. For example, a psychological restriction mechanism such as a siren and / or an alarm may be employed. Furthermore, a mechanism for indirectly restricting movement may be employed by notifying a nearby guard and / or robot, etc., without notifying the person attempting to pass through the gate. Note that the time from when face matching fails until restriction is implemented varies depending on the type of restriction unit employed, but regardless of the means used, it is similarly useful to speed up face matching in order to obtain the results of face matching before the person reaches the restriction unit.

[0150] In other words, the means (restriction unit) for restricting the movement of a person when face matching fails is not limited to an example that physically restricts (blocks) the movement of a person, such as the opening and closing door mechanism 4 provided in the middle of the person's movement path at the gate 400. For example, a specific point (or a specific range) may be set at the gate 400, and the gate 400 may restrict the movement of a person from upstream of the specific point to downstream of the specific point in the direction of the person's movement. In this case, the restriction means may be a siren and / or an alarm, as described above, or a notification to a security guard and / or a robot, etc.

[0151] The present disclosure can be realized in software, hardware, or software in conjunction with hardware.

[0152] Each functional block used in the description of the above embodiments may be partially or entirely realized as an LSI, which is an integrated circuit, and each process described in the above embodiments may be partially or entirely controlled by a single LSI or a combination of LSIs. The LSI may be composed of individual chips, or may be composed of a single chip that includes some or all of the functional blocks. The LSI may have data input and output. Depending on the degree of integration, the LSI may be called an IC, system LSI, super LSI, or ultra LSI.

[0153] The integrated circuit method is not limited to LSI, but may be realized by a dedicated circuit, a general-purpose processor, or a dedicated processor. Also, a field programmable gate array (FPGA) that can be programmed after LSI manufacturing, or a reconfigurable processor that can reconfigure the connections and settings of circuit cells within the LSI, may be used. The present disclosure may be realized as digital processing or analog processing.

[0154] Furthermore, if an integrated circuit technology that can replace LSI emerges due to advances in semiconductor technology or other derivative technologies, it is natural that such technology may be used to integrate functional blocks. The application of biotechnology, etc. is also a possibility.

[0155] The present disclosure may be implemented in any type of apparatus, device, or system (collectively referred to as a communications apparatus) that has a communications function. The communications apparatus may include a wireless transceiver and processing / control circuitry. The wireless transceiver may include a receiver and a transmitter, or both functions. The wireless transceiver (transmitter and receiver) may include a radio frequency (RF) module and one or more antennas. The RF module may include an amplifier, an RF modulator / demodulator, or the like. Non-limiting examples of communication devices include telephones (e.g., cell phones, smartphones), tablets, personal computers (PCs) (e.g., laptops, desktops, notebooks), cameras (e.g., digital still / video cameras), digital players (e.g., digital audio / video players), wearable devices (e.g., wearable cameras, smartwatches, tracking devices), game consoles, digital book readers, telehealth / telemedicine devices, communication-enabled vehicles or mobile transportation (e.g., cars, airplanes, ships), and combinations of the above devices.

[0156] Communications equipment is not limited to portable or mobile equipment, but also includes non-portable or fixed equipment, devices, and systems of any kind, such as smart home devices (such as appliances, lighting equipment, smart meters or metering devices, control panels, etc.), vending machines, and any other "things" that may exist on an IoT (Internet of Things) network.

[0157] Furthermore, in recent years, in the field of IoT (Internet of Things) technology, CPS (Cyber ​​Physical Systems) has been attracting attention as a new concept that creates new added value by linking information between physical space and cyberspace. This CPS concept can also be adopted in the above-mentioned embodiments. That is, as a basic configuration of a CPS, for example, an edge server located in physical space and a cloud server located in cyberspace can be connected via a network, and processing can be distributed and performed by processors installed on both servers. Here, it is preferable that each piece of processing data generated on the edge server or cloud server is generated on a standardized platform, and the use of such a standardized platform can improve the efficiency of building a system that includes a variety of sensor groups and IoT application software.

[0158] Communications include data communications via cellular systems, wireless LAN systems, communications satellite systems, etc., as well as data communications via combinations of these.

[0159] A communications apparatus also includes devices such as controllers and sensors connected or coupled to a communications device that performs the communications functions described in this disclosure, such as controllers and sensors that generate control and data signals used by the communications device to perform the communications functions of the communications apparatus.

[0160] The communication apparatus also includes infrastructure facilities, such as base stations, access points, and any other apparatus, device, or system that communicates with or controls the various apparatuses listed above, but are not limited to these.

[0161] Although various embodiments have been described above with reference to the drawings, it goes without saying that the present disclosure is not limited to such examples. It is clear that a person skilled in the art can conceive of various modifications or alterations within the scope of the claims, and it is understood that these also naturally fall within the technical scope of the present disclosure. Furthermore, the components of the above-described embodiments may be combined in any manner without departing from the spirit of the disclosure.

[0162] Although specific examples of the present disclosure have been described in detail above, these are merely examples and do not limit the scope of the claims. The technology described in the claims includes various modifications and alterations of the specific examples exemplified above. [Industrial Applicability]

[0163] An embodiment of the present disclosure is suitable for a face authentication system. [Explanation of symbols]

[0164] 1, 1a, 1b camera 2 QR code reader 3 Passage control photoelectric sensor 4. Door opening and closing mechanism 5. Entrance guide indicator 6 Passing guide LED 7. Guidance display 8 speakers 9 Interface Board 10 Interface Drivers 20 Gate control device 21a Entrance facial recognition device 21b Exit facial recognition device 30 Network Hubs 100 Facial Recognition System 101, 201 Communications Department 102, 202 Processing section 103b buffer 200, 800 Face Recognition Server 203 Face Registration DB 204 Attendee DB 300 Network 400 gates 400a Entrance Gate 400b Exit Gate 601, 701 processors 602, 702 memory 603, 703 input / output interface Buses 604 and 704 801 Moving range estimation processing unit 802 Travel time DB 803 Exit Candidate DB

Claims

1. an acquisition unit that acquires an image of a person who may be a passenger in a vehicle traveling from a first location to a second location, the image being taken at the first location; a processing unit that determines, based on information about a face image included in the image, candidates of a person who can reach the second location by the vehicle and who is a target of face matching at the second location; Equipped with the processing unit excludes from the candidates persons who are unable to reach the second location by the vehicle by a predetermined time based on information about the time when the face image was taken and information about a theoretical travel time by the vehicle from the first location to the second location calculated based on actual measurements of the behavior of actual visitors and exiting persons; Information processing device.

2. The theoretical travel time uses different values ​​for each time period. The information processing device according to claim 1 .

3. excluding, from the candidates, the person who cannot reach the second point by the vehicle by the predetermined time based on travel time information obtained by adding a margin of the user's stay time in a station to the information on the theoretical travel time; The information processing device according to claim 1 .

4. At least one of the theoretical travel time and the margin uses a different value for each time period. The information processing device according to claim 3 .

5. the processing unit determines the candidate to be prioritized based on information regarding the frequency of use of at least one of the first location and the second location by the person, the person having a higher frequency of use; The information processing device according to claim 1 .

6. the processing unit narrows down information on facial images of people using the vehicle based on information on facial images included in an image captured at the first location, thereby determining the candidates that can reach the second location by the vehicle. The information processing device according to claim 1 .

7. There are a plurality of first locations that can be reached by the vehicle to the second location, the acquisition unit acquires images taken at each of the plurality of first locations. The information processing device according to claim 1 .

8. a camera that photographs, at a first location, a person who may be riding in a vehicle traveling from a first location to a second location; an information processing device that acquires an image captured by the camera and determines, based on facial image information included in the image, candidates for a person who can reach the second location by the vehicle and who is a target of face matching at the second location; Including, the information processing device excludes from the candidates persons who are unable to reach the second location by the vehicle by a predetermined time, based on information on the time when the face image was taken and information on a theoretical travel time by the vehicle from the first location to the second location calculated based on actual measurements of the behavior of actual visitors and exiting persons; Facial recognition system.

9. On the computer, acquiring an image of a person who may be a passenger in a vehicle traveling from a first location to a second location, the image being taken at the first location; determining candidates for persons who can reach the second location by the vehicle and who will be the subject of face matching at the second location, based on information about the facial image included in the image, information about the time when the facial image was taken, and information about the theoretical travel time by the vehicle from the first location to the second location, calculated based on actual measurements of the behavior of actual people entering and leaving the venue; A method of processing information that executes a program.

Images