WO2021256099A1 - 顔認証方法 - Google Patents

顔認証方法 Download PDF

Info

Publication number
WO2021256099A1
WO2021256099A1 PCT/JP2021/016855 JP2021016855W WO2021256099A1 WO 2021256099 A1 WO2021256099 A1 WO 2021256099A1 JP 2021016855 W JP2021016855 W JP 2021016855W WO 2021256099 A1 WO2021256099 A1 WO 2021256099A1
Authority
WO
WIPO (PCT)
Prior art keywords
face
person
face recognition
image
exclusion condition
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2021/016855
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
弘基 横山
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to JP2022532362A priority Critical patent/JP7400975B2/ja
Priority to US18/010,098 priority patent/US20230267788A1/en
Publication of WO2021256099A1 publication Critical patent/WO2021256099A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/30—Individual registration on entry or exit not involving the use of a pass
    • G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
    • G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
    • E—FIXED CONSTRUCTIONS
    • E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
    • E05B—LOCKS; ACCESSORIES THEREFOR; HANDCUFFS
    • E05B49/00—Electric permutation locks; Circuits therefor ; Mechanical aspects of electronic locks; Mechanical keys therefor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/10—Movable barriers with registering means
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition

Definitions

  • the present invention relates to a face recognition method, a face recognition device, and a program.
  • one problem is that even if a companion who accompanies the registrant can enter with a tailgating, such as a child of the registrant, the companion is not allowed to enter. Therefore, when a companion enters the venue, it is necessary to register the companion, which complicates the procedure. Further, as another problem, it is necessary to perform face recognition processing for all persons who can be seen by the camera even if they are accompanied, which increases the processing load for calculating the feature amount of the face image. In this way, in a situation where a companion is accompanied by a registrant, if security is improved as described above, the procedure becomes complicated and the load of face recognition processing increases, so that it is smooth. There is a problem that the face recognition process becomes difficult.
  • an object of the present invention is to provide a face recognition method capable of solving the above-mentioned problem that the face recognition process cannot be smoothly performed when a companion is accompanied by a registrant. To do.
  • the face recognition method which is one embodiment of the present invention, is Extract multiple face images in the captured image and Based on at least one of the face images, it is determined whether or not the person in the face image satisfies the exclusion condition of the face recognition process.
  • the face image of a person satisfying the exclusion condition is excluded, and a face authentication process for authenticating whether or not the person in the face image is a person registered in advance with respect to the other face images is performed. It takes the composition.
  • the face recognition device which is one embodiment of the present invention, is Extraction means to extract multiple face images in the captured image, A determination means for determining whether or not the person in the face image satisfies the exclusion condition of the face authentication process based on at least one of the face images.
  • An authentication means that performs face authentication processing for excluding the face image of a person satisfying the exclusion condition and certifying whether or not the person in the face image is a person registered in advance with respect to the other face image. With, It takes the composition.
  • the program which is one form of the present invention is For information processing equipment Extraction means to extract multiple face images in the captured image, A determination means for determining whether or not the person in the face image satisfies the exclusion condition of the face authentication process based on at least one of the face images. An authentication means that performs face authentication processing for excluding the face image of a person satisfying the exclusion condition and certifying whether or not the person in the face image is a person registered in advance with respect to the other face image. To realize, It takes the composition.
  • the present invention is configured as described above, so that the face recognition process can be smoothly performed when a companion is accompanied by the registrant.
  • FIG. 1 It is a figure which shows an example of the whole structure and the usage situation of the face recognition system in Embodiment 1 of this invention. It is a block diagram which shows the structure of the face recognition apparatus disclosed in FIG. It is a figure which shows an example of the processing of the photographed image by the face recognition apparatus disclosed in FIG. It is a figure which shows another example of the usage situation of the face recognition system disclosed in FIG. It is a figure which shows another example of the usage situation of the face recognition system disclosed in FIG. It is a figure which shows the other example of the processing of the photographed image by the face recognition apparatus disclosed in FIG. It is a flowchart which shows the processing operation by the face recognition apparatus disclosed in FIG.
  • FIGS. 1 to 7. are diagrams for explaining the configuration of the face authentication system
  • FIG. 7 is a diagram for explaining the processing operation of the face authentication system.
  • the face recognition system in the present invention is a system used to authenticate a person from a face image of the person in a specific place such as an office, a store, or an event venue, and to restrict or manage the entry and exit of the person.
  • a specific place is an unmanned store, and from the viewpoint of security, a person registered in advance by taking a face image of a person entering in front of a gate G (door) installed at the entrance / exit of the store. It is determined by face recognition whether or not it is, and if the authentication is successful, the gate G is opened to allow the person to enter.
  • the face recognition system of the present invention is not necessarily limited to being installed at the gate G of the store, and may be installed at any place. Further, the face recognition system of the present invention does not necessarily have to open the gate G according to the result of face recognition, and may be used for any processing such as using the result of face recognition for payment.
  • the face recognition system is installed at an arbitrary location, such as a gate G installed in an unmanned store, a camera C which is a photographing device installed next to the gate G, and a display D which is a display device. It is equipped with a face recognition device 1 and the like.
  • the gate G is an automatic door that serves as an entrance / exit to an unmanned store, and is opened / closed in response to a command from the face recognition device 1 as described later.
  • the gate G is dedicated to the entrance to the unmanned store.
  • the camera C is installed at a position where a user who visits an unmanned store, that is, a user standing in front of the gate G, can be photographed.
  • the height and angle of view of the camera C are set so that an image including the face of a user of any height can be captured. Then, the camera C constantly captures an image and transfers the captured image to the face recognition device 1.
  • the position where the camera C is installed is not limited to the above-mentioned position.
  • the display D is installed below the camera C, and is installed at a position where it can be visually recognized by a user who turns his face to the camera C for face recognition. Then, the display D displays, for example, information indicating success or failure of authentication as a result of the face recognition process transmitted from the face recognition device 1 as described later.
  • the position where the display D is installed is not limited to the above-mentioned position.
  • the face recognition device 1 is composed of one or a plurality of information processing devices including an arithmetic unit and a storage device. Then, as shown in FIG. 2, the face recognition device 1 includes an image acquisition unit 11, a face extraction unit 12, an exclusion determination unit 13, a face authentication unit 14, and a gate control unit 15. The functions of the image acquisition unit 11, the face extraction unit 12, the exclusion determination unit 13, the face authentication unit 14, and the gate control unit 15 are such that the arithmetic unit executes a program for realizing each function stored in the storage device. , Can be realized. Further, the face recognition device 1 includes a user information storage unit 16. The user information storage unit 16 is composed of a storage device. Hereinafter, each configuration will be described in detail.
  • the image acquisition unit 11 first acquires a facial image of a user who wishes to be registered in an unmanned store, and stores the facial image in the user information storage unit 16. For example, when the person P1 shown in FIG. 1 wishes to become a registrant of an unmanned store, the face image taken by the person P1 himself or the face image of the person P1 taken by the person in charge of the store is acquired. And store it as user information. As for the face image of the person P1 as a registrant, the feature amount of the face image may be calculated and the feature amount may be stored as described later. Further, the user information includes a name, contact information, payment information, and the like, as well as a face image of the person P1 who is a registrant.
  • the image acquisition unit 11 receives images taken by the camera C in front of the gate G of the unmanned store at regular time intervals. For example, as shown in FIG. 1, when two people P1 and P2 are located in front of the store, as shown in FIG. 3, a photographed image including the facial images of the two people P1 and P2 is captured. It will be acquired.
  • the two persons P1 and P2 shown in FIG. 1 are the registrant P1 of the unmanned store, and the other one is not registered for use in the unmanned store and is a child of the registrant P1. , The companion P2 who visited the unmanned store with the registrant P1.
  • the face extraction unit 12 extracts a person in the photographed image from the shape, color, movement, etc. of the object reflected in the photographed image, and further extracts the face image area of the person. For example, as shown in FIG. 3, the face extraction unit 12 extracts the face image area R1 of the registrant person P1 and the face image area R2 of the companion person P2, respectively. At this time, when a plurality of face images appearing at the same time exist in the captured image, the face extraction unit 12 collectively extracts a plurality of face image areas and associates the plurality of face image areas with each other. For example, as shown in FIG.
  • the exclusion determination unit 13 determines whether or not the persons P1 and P2 in the face image areas R1 and R2 extracted as shown in FIG. 3 satisfy the exclusion condition of the face authentication process described later. At this time, when the plurality of face image areas R1 and R2 are extracted, the exclusion determination unit 13 satisfies the exclusion condition of the face recognition process for each person P1 and P2 in each face image area R1 and R2. Judge whether or not. Specifically, the exclusion determination unit 13 detects the age (age) of each person P1 and P2 as an attribute of each person P1 and P2 based on the face image of each face image area R1 and R2, and the attribute is Determine if the exclusion condition is met.
  • the exclusion determination unit 13 detects the age from the features on the facial images by performing preset analysis processing on the facial images of the persons P1 and P2. For example, when the exclusion determination unit 13 detects an age group such as "old man”, “adult”, or “child”, in the example of FIG. 3, the person P1 is detected as an attribute such as "adult”, and the person P2. Detects as an attribute such as "children”.
  • the exclusion determination unit 13 indicates that the person P1 does not satisfy the exclusion condition of the face authentication process and the person P2 does not satisfy the exclusion condition. It is determined that the exclusion condition of the face recognition process is satisfied.
  • the exclusion determination unit 13 calculates the value of the age of the person based on the face image, and if it is lower than the threshold age that can be determined as a preset child, the exclusion condition of the face authentication process is satisfied. You may judge.
  • the exclusion determination unit 13 determines whether or not the exclusion condition of the face authentication process is satisfied for the person in at least one face image area. May be determined.
  • the attribute may be detected only for the face image area R2 of the person P2, and it may be determined whether or not the person P2 satisfies the exclusion condition of the face authentication process.
  • the face image area R2 of the person P2 satisfies the exclusion condition of the face authentication process, but the face image area R1 of the undetermined person P1 is treated as not satisfying the exclusion condition of the face authentication process.
  • the face recognition process will be performed as described later.
  • the exclusion determination unit 13 is not necessarily limited to detecting an attribute such as the age of a person by using only the face image in the face image area.
  • the attributes of a person may be detected by using the height of the person detected from the captured image, the posture of the person, the size of the face area, and the like.
  • three people P11, P12, and P13 are shown in the captured image, but one person for two people P11 and P12 is combined with age detection by the feature on the face image.
  • the attribute of the person P13 may be determined as "child" based on the height difference of the person P13. Further, in the example of FIG.
  • the face image areas R21 and R22 of the two persons P21 and P22 are extracted, and the attributes of the persons P21 and P22 are determined based on the distances of the face image areas R21 and R22. It may be detected.
  • the two face image areas R21 and R22 are located at extremely short distances and within a preset distance range, it is determined that an adult is holding a child, and one person The attribute of the person P21 may be detected as "adult", and the attribute of the other person P22 may be detected as "child”.
  • the exclusion determination unit 13 may detect the attributes of the persons P21 and P22 by referring to the positional relationship and posture of the persons P21 and P22.
  • the exclusion determination unit 13 may detect not only age but also other attributes as the attributes of the person. For example, the exclusion determination unit 13 may detect an attribute such as the gender of a person based on the characteristics of the face image in the face image area. In this case, the exclusion determination unit 13 determines, for example, that when the unmanned store is a store that handles products for women, a person with a female attribute satisfies the exclusion condition of the face recognition process.
  • the attributes and exclusion conditions detected by the exclusion determination unit 13 described above are examples, and any attributes may be detected and any exclusion conditions may be set.
  • the exclusion determination unit 13 detection processing of a person's attribute, analysis processing is performed on a person image including a person's face image, but the processing load and calculation amount of the analysis processing will be described later. It is smaller than the processing load and the calculation amount at the time of calculating the feature amount of the face image performed at the time of the face recognition processing of the person.
  • the exclusion determination unit 13 exemplifies a case where the face image is analyzed to detect age features and a case where the face distance is calculated, but these analysis processes are face recognition of a person. This processing is less than the processing load and calculation amount in the face image feature amount calculation performed at the time of processing.
  • the face recognition unit 14 excludes the face image area determined to satisfy the exclusion condition of the face recognition process as described above, and only for the face image area determined not to satisfy the exclusion condition. Perform face recognition processing. Therefore, in the example of FIG. 3, the face recognition process is performed on the face image area R1 of the person P1 whose attribute is determined to be "adult", and the face image area R2 of the person P2 whose attribute is determined to be "child” is performed. Face recognition processing is not performed on the face. Specifically, the face recognition unit 14 first calculates the feature amount of the face image in the face image area as the face recognition process.
  • the similarity between the calculated feature amount and the feature amount of the face image of the registrant stored in the user information storage unit 16 is calculated, and the person P1 is the registrant from the similarity degree. Authenticate whether or not. At this time, if the similarity between the features of the face image is equal to or higher than the threshold value, it is determined that the person P1 is the registrant, and it is determined that the face authentication process is successful. However, as described above, the face image area for which the face authentication process is performed by the face authentication unit 14 is treated as not satisfying the exclusion condition because it is not determined whether or not the exclusion condition is satisfied. Will also be included.
  • the face recognition unit 14 performs face recognition processing on the face image areas of the two persons P11 and P12 whose attributes are determined to be "adults", respectively, and the attribute is "children". The face recognition process is not performed on the face image area of the person P13 determined to be. Further, in the example of FIG. 6, the face recognition unit 14 performs face recognition processing on the face image area of the person P21 whose attribute is determined to be "adult", and the person P22 whose attribute is determined to be "child”. Face recognition processing is not performed on the face image area of.
  • the gate control unit 15 controls to open the gate G when the face recognition process described above is successful.
  • the gate control unit 15 opens the gate G without performing the face authentication process of the person P2 who is the companion and registers.
  • the person P1 who is a person and the person P2 who is a companion are allowed to enter the unmanned store.
  • the gate control unit 15 when the persons P11 and P12 are registrants and the face authentication processing of the persons P11 and P12 is successful, the face authentication of the accompanying person P13 is performed.
  • the gate G is opened without any processing, and the registrants P11 and P12 and the accompanying person P13 are allowed to enter the unmanned store.
  • the gate control unit 15 may control to open the gate only when the authentication of all the persons P11 and P12 who have performed the face authentication process is successful, but the gate control unit 15 may control the gate to be opened, but the plurality of persons P11 who have performed the face authentication process.
  • the gate may be opened. That is, if there is even one registrant for a group of a plurality of persons and the face recognition process is successful, the gate may be opened to allow all other companions to enter. Further, in the example of FIG.
  • the gate control unit 15 performs the face authentication process of the person P22 who is the companion. Instead, the gate G is opened to allow the registrant P21 and the companion P22 to enter the unmanned store.
  • the gate control unit 15 may receive the result of the face authentication process and output the information according to the result of the face authentication process to the display D. For example, the gate control unit 15 outputs to indicate that the face recognition process is successful or that the gate G is opened, and if the face recognition process fails, the gate control unit 15 indicates that the authentication has failed. Output to display the information that the gate G cannot be opened.
  • the gate control unit 15 may output any information by any device, such as outputting an alarm to the effect that authentication has failed by turning on a lamp (not shown) installed around the gate G.
  • the face recognition device 1 always acquires an image taken in front of the gate G, which is the entrance of the unmanned store, from the camera C (step S1). Then, the face recognition device 1 extracts a face image area of a person from the acquired photographed image. For example, as shown in FIG. 3, the face recognition device 1 extracts the face image area R1 of the registrant person P1 and the face image area R2 of the companion person P2 (step S2).
  • step S4 when the face recognition device 1 has a plurality of face image areas R1 and R2 extracted as shown in FIG. 3 (Yes in step S3), the face recognition device 1 of each person P1 and P2 in each face image area R1 and R2. Detect age (step S4). For example, in the example of FIG. 3, the ages of the persons P1 and P2 are detected from the features of the face images in the face image areas R1 and R2. Further, in the example of FIG. 6, since the distances of the face image areas R21 and R22 are short, the ages of the persons P1 and P2 are detected.
  • the face recognition device 1 determines that the child person satisfies the exclusion condition of the face authentication process, and determines that the face image area of the person is satisfied. Is excluded from the face recognition process (step S6). For example, in the example of FIG. 3, when the face recognition device 1 detects that the person P1 is the age of an "adult” and the person P2 is the age of a "child", the person P1 satisfies the exclusion condition of the face recognition process. Instead, it is determined that the person P2 satisfies the exclusion condition of the face recognition process. In this way, the face recognition device 1 detects the attribute of the person before calculating the feature amount of the face image for face recognition in the face recognition processing later, and determines whether or not the exclusion condition of the face recognition processing is satisfied. Is determined.
  • the face recognition device 1 performs face recognition processing only on the face image area determined not to satisfy the exclusion condition, excluding the face image area determined to satisfy the exclusion condition of the face recognition processing. Therefore, in the examples of FIGS. 3 and 6, the face recognition process is performed on the face image area R1 of the person P1 whose attribute is determined to be "adult", and the face of the person P2 whose attribute is determined to be "child". Face recognition processing is not performed on the image area R2. Specifically, as the face recognition process, the face recognition device 1 first calculates the feature amount for the face recognition process of the face image in the face image area R1 (step S7).
  • step S8 the similarity between the calculated feature amount and the feature amount of the face image of the registrant registered in advance as user information is calculated, and whether or not the person P1 is a registrant is obtained from the similarity. Authentication is performed (step S8).
  • the face recognition device 1 determines that the person P1 is a registrant, and if the face recognition process is successful (Yes in step S9), the face recognition device 1 controls to open the gate G (step S10). On the other hand, when the face recognition process fails, the face recognition device 1 outputs alarm information indicating that the authentication has failed or that the gate cannot be released (step S11).
  • the face images of a plurality of persons are extracted, it is determined from the face images whether or not the person satisfies the exclusion condition of the face recognition process, and the face image satisfying the exclusion condition is a face.
  • Face recognition processing is performed only for other face images without performing authentication. Therefore, if the companion of the person who is the registrant who should perform face recognition meets the exclusion condition of the face recognition processing such as a child, the face recognition processing of the companion is not performed, so that extra face recognition is performed. It is possible to suppress the processing from being executed.
  • FIGS. 8 to 10 are block diagrams showing the configuration of the face recognition device according to the second embodiment
  • FIG. 10 is a flowchart showing the operation of the face recognition device.
  • the outline of the configuration of the face recognition device and the face recognition method described in the above-described embodiment is shown.
  • the face recognition device 100 is composed of a general information processing device, and is equipped with the following hardware configuration as an example.
  • -CPU Central Processing Unit
  • -ROM Read Only Memory
  • RAM Random Access Memory
  • 103 storage device
  • -Program group 104 loaded in RAM 103
  • a storage device 105 for storing the program group 104.
  • a drive device 106 that reads / writes the storage medium 110 external to the information processing device.
  • -Communication interface 107 that connects to the communication network 111 outside the information processing device.
  • -I / O interface 108 for inputting / outputting data -Bus 109 connecting each component
  • the face recognition device 100 can construct and equip the extraction means 121, the determination means 122, and the authentication means 123 shown in FIG. 9 by acquiring the program group 104 by the CPU 101 and executing the program group 104. ..
  • the program group 104 is stored in, for example, a storage device 105 or a ROM 102 in advance, and the CPU 101 loads the program group 104 into the RAM 103 and executes the program group 104 as needed. Further, the program group 104 may be supplied to the CPU 101 via the communication network 111, or may be stored in the storage medium 110 in advance, and the drive device 106 may read the program and supply the program to the CPU 101.
  • the extraction means 121, the determination means 122, and the authentication means 123 described above may be constructed by a dedicated electronic circuit for realizing such means.
  • FIG. 8 shows an example of the hardware configuration of the information processing device, which is the face recognition device 100, and the hardware configuration of the information processing device is not limited to the above case.
  • the information processing device may be configured from a part of the above-mentioned configuration, such as not having the drive device 106.
  • the face recognition device 100 executes the face recognition method shown in the flowchart of FIG. 10 by the functions of the extraction means 121, the determination means 122, and the authentication means 123 constructed by the program as described above.
  • the face recognition device 100 is Extracting a plurality of face images in the captured image (step S101), Based on at least one of the face images, it is determined whether or not the person in the face image satisfies the exclusion condition of the face authentication process (step S102). The face image of a person satisfying the exclusion condition is excluded, and a face authentication process for authenticating whether or not the person in the face image is a person registered in advance with respect to the other face images is performed (step S103). , Is executed.
  • the present invention is configured as described above, extracts facial images of a plurality of persons, determines whether or not the person satisfies the exclusion condition of the face recognition process from the face image, and satisfies the exclusion condition. Face recognition is not performed for face images, and face recognition processing is performed only for other face images. Therefore, if the companion of the person who is the registrant who should perform face recognition meets the exclusion condition of the face recognition processing, the face recognition processing of the companion is not performed, so that extra face recognition processing is performed. It is possible to suppress the execution and realize smooth face recognition processing.
  • Non-temporary computer-readable media include various types of tangible storage media.
  • Examples of non-temporary computer-readable media include magnetic recording media (eg, flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (eg, magneto-optical disks), CD-ROMs (ReadOnlyMemory), CD-Rs, Includes CD-R / W, semiconductor memory (eg, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (RandomAccessMemory)).
  • the program may also be supplied to the computer by various types of temporary computer readable medium. Examples of temporary computer-readable media include electrical, optical, and electromagnetic waves.
  • the temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.
  • the invention of the present application has been described above with reference to the above-described embodiments and the like, the invention of the present application is not limited to the above-described embodiments. Various changes that can be understood by those skilled in the art can be made to the structure and details of the present invention within the scope of the present invention. Further, at least one or more of the functions of the extraction means 121, the determination means 122, and the authentication means 123 described above may be executed by an information processing device installed and connected to any place on the network, that is, , May be executed by so-called cloud computing.
  • Appendix 2 The face recognition method described in Appendix 1 An attribute of a person in the face image is detected based on at least one of the face images, and it is determined whether or not the exclusion condition is satisfied based on the attribute. Face recognition method. (Appendix 3) The face recognition method described in Appendix 2, The age of the person in the face image is detected based on at least one of the face images, and it is determined whether or not the exclusion condition is satisfied based on the age. Face recognition method. (Appendix 4) The face recognition method described in Appendix 3 When the age of the person in the facial image is an age that can be determined to be a child according to a preset standard, it is determined that the exclusion condition is satisfied. Face recognition method.
  • Face recognition method Before performing the feature amount calculation for the face image required for the face recognition processing, it is determined whether or not the person in the face image satisfies the exclusion condition based on the face image.
  • Face recognition method (Appendix 7) The face recognition method according to any one of Supplementary note 1 to 6, wherein the face recognition method is used.
  • the face recognition process for at least one other face image excluding the face image of a person who satisfies the exclusion condition is successful among the plurality of face images simultaneously extracted from the captured image, it is predetermined. Control to open the gate of Face recognition method.
  • Appendix 8 The face recognition method described in Appendix 7 When the face recognition process for all the other face images excluding the face image of the person who satisfies the exclusion condition is successful among the plurality of face images simultaneously extracted from the captured image, a predetermined value is specified. Control to open the gate, Face recognition method. (Appendix 9) Extraction means to extract multiple face images in the captured image, A determination means for determining whether or not the person in the face image satisfies the exclusion condition of the face authentication process based on at least one of the face images. An authentication means that performs face authentication processing for excluding the face image of a person satisfying the exclusion condition and certifying whether or not the person in the face image is a person registered in advance with respect to the other face image.
  • Face recognition device equipped with (Appendix 9.1) The face recognition device according to Appendix 9, The determination means detects an attribute of a person in the face image based on at least one face image, and determines whether or not the exclusion condition is satisfied based on the attribute. Face recognition device. (Appendix 9.2) The face recognition device described in Appendix 9.1. The determination means detects the age of a person in the face image based on at least one face image, and determines whether or not the exclusion condition is satisfied based on the age. Face recognition device. (Appendix 9.3) The face recognition device described in Appendix 9.2. The determination means determines that the exclusion condition is satisfied when the age of the person in the face image is an age that can be determined to be a child according to a preset standard.
  • Face recognition device (Appendix 9.4) The face recognition device according to any one of Supplementary note 9 to 9.3.
  • the determination means detects an attribute of at least one person in the face image based on the plurality of face images, and determines whether or not the exclusion condition is satisfied based on the attribute.
  • Face recognition device (Appendix 9.5) The face recognition device described in Appendix 9.4.
  • the determination means detects the age of at least one person in the face image based on the distance of each person in the plurality of face images, and determines whether or not the exclusion condition is satisfied based on the age.
  • Face recognition device (Appendix 9.6) The face recognition device according to any one of Supplementary note 9 to 9.5.
  • the determination means determines whether or not the person in the face image satisfies the exclusion condition based on the face image before performing the feature amount calculation for the face image required for the face recognition processing.
  • Face recognition device (Appendix 9.7) The face recognition device according to any one of Supplementary note 9 to 9.6. When the face authentication process for at least one other face image excluding the face image of a person who satisfies the exclusion condition is successful among the plurality of face images simultaneously extracted from the captured image, a predetermined value is obtained.
  • Gate control means which controls to open the gate of Face recognition device equipped with.
  • Appendix 9.8 The face recognition device described in Appendix 9.7.
  • the gate control means succeeds in the face recognition processing for all the other face images except the face image of the person who satisfies the exclusion condition among the plurality of face images simultaneously extracted from the captured image. If you do, control to open the given gate, Face recognition device. (Appendix 10) For information processing equipment Extraction means to extract multiple face images in the captured image, A determination means for determining whether or not the person in the face image satisfies the exclusion condition of the face authentication process based on at least one of the face images. An authentication means that performs face authentication processing for excluding the face image of a person satisfying the exclusion condition and certifying whether or not the person in the face image is a person registered in advance with respect to the other face image. A program to realize.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Collating Specific Patterns (AREA)
  • Lock And Its Accessories (AREA)
PCT/JP2021/016855 2020-06-17 2021-04-27 顔認証方法 Ceased WO2021256099A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022532362A JP7400975B2 (ja) 2020-06-17 2021-04-27 顔認証方法
US18/010,098 US20230267788A1 (en) 2020-06-17 2021-04-27 Face authentication method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020-104263 2020-06-17
JP2020104263 2020-06-17

Publications (1)

Publication Number Publication Date
WO2021256099A1 true WO2021256099A1 (ja) 2021-12-23

Family

ID=79267747

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/016855 Ceased WO2021256099A1 (ja) 2020-06-17 2021-04-27 顔認証方法

Country Status (3)

Country Link
US (1) US20230267788A1 (https=)
JP (1) JP7400975B2 (https=)
WO (1) WO2021256099A1 (https=)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2023187960A1 (https=) * 2022-03-29 2023-10-05
WO2024241660A1 (ja) * 2023-05-24 2024-11-28 パナソニックＩｐマネジメント株式会社 人物照合システム、情報処理装置、人物照合方法、及び、人物照合プログラム

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7249555B2 (ja) * 2021-04-16 2023-03-31 パナソニックＩｐマネジメント株式会社 情報処理装置、及び、情報処理方法
JP2024135205A (ja) * 2023-03-22 2024-10-04 株式会社東芝 通行管理プログラム、通行管理方法、及び通行管理装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0773298A (ja) * 1993-09-07 1995-03-17 Sharp Corp 人物認識装置
JP2010061465A (ja) * 2008-09-04 2010-03-18 Sony Corp 画像処理装置、撮像装置、画像処理方法およびプログラム
JP2016146073A (ja) * 2015-02-09 2016-08-12 株式会社日立製作所 入場制御システム
JP2019053674A (ja) * 2017-09-19 2019-04-04 日本電気株式会社 照合システム
JP2019133364A (ja) * 2018-01-31 2019-08-08 日本電気株式会社 情報処理装置
WO2020075308A1 (ja) * 2018-10-12 2020-04-16 日本電気株式会社 情報処理装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5276315B2 (ja) * 2007-12-21 2013-08-28 キヤノン株式会社 認証システム、情報処理装置および制御方法
JP6621033B2 (ja) * 2016-11-08 2019-12-18 パナソニックＩｐマネジメント株式会社 年齢確認システム、及びそれを備えた買物支援システム
US10679443B2 (en) * 2017-10-13 2020-06-09 Alcatraz AI, Inc. System and method for controlling access to a building with facial recognition
DE102019203324A1 (de) * 2019-03-12 2020-09-17 Robert Bosch Gmbh Überwachungsvorrichtung, Überwachungsanlage, Verfahren, Computerprogramm und maschinenlesbares Speichermedium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0773298A (ja) * 1993-09-07 1995-03-17 Sharp Corp 人物認識装置
JP2010061465A (ja) * 2008-09-04 2010-03-18 Sony Corp 画像処理装置、撮像装置、画像処理方法およびプログラム
JP2016146073A (ja) * 2015-02-09 2016-08-12 株式会社日立製作所 入場制御システム
JP2019053674A (ja) * 2017-09-19 2019-04-04 日本電気株式会社 照合システム
JP2019133364A (ja) * 2018-01-31 2019-08-08 日本電気株式会社 情報処理装置
WO2020075308A1 (ja) * 2018-10-12 2020-04-16 日本電気株式会社 情報処理装置

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2023187960A1 (https=) * 2022-03-29 2023-10-05
WO2023187960A1 (ja) * 2022-03-29 2023-10-05 日本電気株式会社 認証システム、認証方法およびコンピュータ可読媒体
JP7810255B2 (ja) 2022-03-29 2026-02-03 日本電気株式会社 認証システム、認証方法およびプログラム
WO2024241660A1 (ja) * 2023-05-24 2024-11-28 パナソニックＩｐマネジメント株式会社 人物照合システム、情報処理装置、人物照合方法、及び、人物照合プログラム

Also Published As

Publication number Publication date
US20230267788A1 (en) 2023-08-24
JPWO2021256099A1 (https=) 2021-12-23
JP7400975B2 (ja) 2023-12-19

Similar Documents

Publication Publication Date Title
WO2021256099A1 (ja) 顔認証方法
US20230342451A1 (en) Information processing device
JP7196932B2 (ja) 情報処理装置、情報処理方法、およびプログラム
CN104008317B (zh) 认证设备和认证方法
JP7704277B2 (ja) ゲート装置、出入国審査システム、ゲート装置の制御方法及びプログラム
CN116917952A (zh) 用于筛查用户体温的方法和系统
AU2020436230A1 (en) Gate device, authentication system, gate control method, and storage medium
JP7251874B2 (ja) 顔認証装置、顔認証方法、プログラム、および記録媒体
JP7509216B2 (ja) 入力制御装置、入力システム、入力制御方法及び入力制御プログラム
WO2019138688A1 (ja) 顔認証装置
JP7192850B2 (ja) 情報取得システム、情報取得装置、サーバ、情報端末及び情報取得方法
JP7632532B2 (ja) ゲート装置、ゲート装置の制御方法及びプログラム
JP4910717B2 (ja) 年齢確認装置、年齢確認方法、及び年齢確認プログラム
WO2021176593A1 (ja) 滞在管理装置、滞在管理方法、プログラムが格納された非一時的なコンピュータ可読媒体、及び滞在管理システム
JP2018077552A (ja) ゲート管理システムおよび方法
WO2019151116A1 (ja) 情報処理装置
WO2023152937A1 (ja) システム、サーバ装置、サーバ装置の制御方法及び記憶媒体
US12198489B2 (en) Information processing apparatus, information processing method, and storage medium
WO2021060256A1 (ja) 顔認証装置、顔認証方法、及びコンピュータ読み取り可能な記録媒体
KR102777663B1 (ko) 얼굴 인식 시스템 및 얼굴 인식 시스템을 위한 제어 방법
WO2022003852A1 (ja) 認証制御装置、認証制御システム、認証制御方法及び非一時的なコンピュータ可読媒体
US12530440B2 (en) Information processing device, permission determination method, and program
US12548393B2 (en) System, gate device, control method for gate device, and storage medium
KR102233254B1 (ko) 사용자의 생체 정보에 기초하여 출입을 통제하는 방법 및 이를 위한 전자잠금시스템
WO2023145059A1 (ja) 入場管理装置、入場管理方法およびプログラム記憶媒体

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21826569

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022532362

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21826569

Country of ref document: EP

Kind code of ref document: A1