JP2005107588A - Personal verification system and ingress/egress management system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a personal verification system capable of increasing verifying accuracy by eliminating the influence of a difference in the environment where the system is installed, such as illumination, when dictionary information is distributed to a biometric device different from another biometric device in which the dictionary information is registered. <P>SOLUTION: A plurality of personal verification devices are interconnected via a network. One of the personal verification devices is used as a registering device for dictionary information and the other personal verification devices are used as verification devices for verifying faces. When the dictionary information is distributed from the personal verification device serving as the registering device to the other personal verification devices serving as the verification devices, the personal verification devices each perform a one-to-one matching using the dictionary information and, if the matching was successful, update the dictionary information. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention is provided, for example, at least one biometric registration device for registering unique biometric information of a person to be collated as dictionary information and a plurality of locations different from the biometric registration device, and the biometric registration A plurality of biological bodies that are connected to the apparatus via a communication line and determine whether or not the person to be collated is the person by collating the input unique biometric information with the dictionary information distributed from the biometric registration apparatus. The present invention relates to a person collation system that includes a collation device and can collate at a plurality of points, and an entry / exit management system that manages entry / exit with respect to a security area or the like using the person collation system.

  For example, by installing biometric verification devices that perform biometric information such as facial images at multiple locations, and connecting these multiple biometric verification devices via a network, verification at multiple points There is a person verification system that makes it possible.

In such a person verification system, for example, by using one biometric verification device among a plurality of biometric verification devices as a biometric registration device, in this biometric verification device (biological registration device), a unique biometric of the person to be verified By registering information (for example, face image) as dictionary information and distributing the registered dictionary information to other biometric matching devices via the network, each biometric matching device uses the distributed dictionary information. There is something that is to be verified.
JP-A-11-175718

  As described above, when dictionary information is distributed and collated to a biometric collation device that is different from the biometric collation device that registered the dictionary information, the difference in the installation environment such as lighting from the location where the dictionary information is registered is collated. Accuracy can be greatly affected.

  Further, in the 1-to-N collation that collates with all registered dictionary information, the smaller the number of persons to be collated, the smaller the number of persons who judge the difference from others, and thus the collation accuracy is improved. On the other hand, when a plurality of biometric matching devices are connected by a network and dictionary information registered in a certain biometric matching device is distributed to other biometric matching devices, the same number of dictionary information exists in all the biometric matching devices. Therefore, the number of people who can perform one-to-N matching becomes the number of people that can be registered in the entire system, which also affects the matching accuracy.

  Therefore, the present invention eliminates the influence of differences in the installation environment such as lighting and improves collation accuracy when the dictionary information is distributed to a biometric collation device that is different from the biometric collation device that registered the dictionary information. An object of the present invention is to provide a person verification system and an entrance / exit management system that can be used.

  The person collation system of the present invention is installed in at least one biometric registration device for registering unique biometric information of a collation target person as dictionary information, and at a location different from the biometric registration device, and the biometric registration device At least one or more that determines whether or not the person to be collated is the person by collating the input unique biometric information with the dictionary information distributed from the biometric registration device. The biometric registration device is configured to acquire first specific information acquisition means for acquiring specific information for specifying a person to be verified, and first to acquire specific biometric information of the person to be verified. 1 biological information acquisition means, dictionary creation means for creating dictionary information from the biological information obtained by the first biological information acquisition means, and dictionary information created by the dictionary creation means as the first Distribution means for distributing to the biometric matching device together with the specific information acquired by the specific information acquiring means, and the biometric matching device receives the dictionary information and the specific information distributed by the distribution means of the biometric registration device. Receiving means, dictionary storage means for storing the dictionary information and specific information received by the receiving means in correspondence with each other, second specific information acquiring means for acquiring specific information for specifying a person to be verified, and a verification target Second biological information acquisition means for acquiring a person's unique biological information, biological information acquired by the second biological information acquisition means, and the second specific information acquisition means stored in the dictionary storage means Collation means for judging whether or not a predetermined relationship is established between both pieces of information by collating with the acquired specific information and corresponding dictionary information, and the result of collation by this collation means The biometric information acquired by the second biometric information acquisition means is the dictionary information stored in the dictionary storage means when the collation is successful when a predetermined relationship is established between the acquired biometric information and the dictionary information. Dictionary updating means for updating based on the above.

  Moreover, the entrance / exit management system of the present invention is installed at a location different from the biometric registration device, and at least one biometric registration device for registering the biometric information unique to the person to be verified as dictionary information, At least a determination is made as to whether or not the person to be collated is the person himself / herself by collating the input unique biometric information with the dictionary information distributed from the biometric registration apparatus. One or more biometric matching devices and an entrance / exit control device that is connected to the biometric matching device via a communication line and controls opening / closing of a passage gate for entering / exiting based on a matching result of the biometric matching device. The biometric registration device is configured to obtain first specific information acquisition means for acquiring specific information for specifying a person to be verified, and first biometric information acquisition for acquiring unique biometric information of the person to be verified And dictionary creating means for creating dictionary information from the biological information obtained by the first biological information obtaining means, and dictionary information created by the dictionary creating means is obtained by the first specific information obtaining means. Distribution means for delivering to the biometric matching device together with the specific information, wherein the biometric matching device includes first receiving means for receiving the dictionary information and the specific information delivered by the distribution means of the biometric registration device; Dictionary storage means for storing the dictionary information and specific information received by the first receiving means in correspondence with each other, second specific information acquisition means for acquiring specific information for specifying the person to be verified, Second biological information acquisition means for acquiring unique biological information, biological information acquired by the second biological information acquisition means, and the second specific information stored in the dictionary storage means Collation means for judging whether or not a predetermined relationship is established between both pieces of information by collating the specific information obtained by the obtaining means with the corresponding dictionary information; When the collation is successful in which a predetermined relationship is established between the biometric information and the dictionary information, the entry / exit control is performed to inquire whether or not the person to be collated is a pass-perm permitted to pass to the pass gate. The entrance / exit control device, the access permission information indicating whether or not the person to be verified is a pass-permitted person who is allowed to pass to the pass gate; By referring to the passability information in response to an inquiry from the inquiry means of the biometric matching device whether or not the verification target person is a permitted person, the verification target person is permitted to pass to the traffic gate. A determination unit that determines whether or not the person is permitted to pass, and a transmission unit that transmits a determination result of the determination unit to the biometric matching device. The biometric matching device includes the entrance / exit control device. If the determination result received by the second receiving means and the determination result received by the second receiving means is a passer, the dictionary storage means stores the result. And dictionary updating means for updating the dictionary information based on the biological information acquired by the second biological information acquiring means.

  According to the present invention, when dictionary information is distributed to a biometric matching device that is different from the biometric matching device that registered the dictionary information, the influence of differences in the installation environment such as lighting is obtained by capturing the environment information of the distribution destination. Therefore, it is possible to provide a person verification system and an entrance / exit management system that can improve verification accuracy.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
In the following description, a case where a face image is used as the biological information of a person will be described as an example. However, in addition to the face image, a fingerprint image, an iris information, a palm-shaped image, a finger image, voice information, rhythm information, etc. The same can be implemented using other biological information.

  FIG. 1 schematically shows a configuration of an entrance / exit management system to which the person verification system according to the present embodiment is applied. In FIG. 1, a plurality of person verification devices (biometric verification devices) 11, 12, 13, 14, each capable of dictionary registration and face verification, are installed in different places, and are connected via a network (communication line) 15. So that they can communicate with each other.

  The person verification devices 11, 12, 13, and 14 are connected to the entrance / exit control devices 16, 17, 18, and 19, respectively. The entrance / exit control devices 16, 17, 18, 19 are respectively provided with electric locks 21, 22, 23, 24 provided at entrance / exit gates based on the verification results from the person verification devices 11, 12, 13, 14. Open / close control.

  An entrance / exit management server 25 is connected to the entrance / exit control devices 16, 17, 18, 19. The entrance / exit management server 25 manages the entrance / exit control devices 16, 17, 18, 19, and traffic area information (passability information) for managing the pass permission of the person to be verified for each pass gate, day of the week, and time zone. ) And this traffic area information is distributed to each of the entrance / exit control devices 16, 17, 18, and 19, respectively.

  For example, as shown in FIG. 2, person collation apparatuses 11, 12, 13, and 14 capture and input a face image (an image including at least a face) of person 100 to be collated (hereinafter also referred to as a person). The television camera 101 as the biometric information acquisition unit, the illumination unit 102 as the illumination unit that irradiates light at a constant illuminance toward at least the face of the verification target person 100 from the vicinity of the camera 101, and input to the verification target person 100 An input / output unit 103 as a display means and a specific information acquisition means for displaying a displayed face image, various types of guidance, etc., or inputting an ID number (specific information), a password, etc. for specifying the person 100 to be verified; The processing unit 104 is configured to process a face image input from the camera 101 and perform face image recognition processing or the like.

  In the following description, image input data, extracted feature quantities, subspaces, eigenvectors for constructing the subspace, correlation matrix, registration time, date and time, status information such as location, password, ID number, etc. Each piece of personal information appears. And when it says recognition data, it contains the eigenvector for comprising a partial space or a partial space, and when it says registration information (dictionary information), it is image input data, the extracted feature-value, partial space, partial space. Includes an eigenvector, a correlation matrix, situation information, and personal information. Accordingly, the recognition data is included in the registration information.

  The camera 101 captures and inputs a face image of the person 100 to be collated from below at a predetermined angle. For example, the camera 101 includes a television camera using an image sensor such as a CCD sensor.

  The illuminating unit 102 is an illuminating device such as a fluorescent lamp that emits light at a constant illuminance from the vicinity of the camera 101 (for example, the side of the camera 101) toward the face of the person 100 to be verified.

  The input / output unit 103 displays the face image of the verification target person 100 photographed by the camera 101, various guidances, processing results, etc., and inputs the personal ID and password of the verification target person 100. For example, the liquid crystal display unit and the touch panel are integrated, and are provided in the vicinity of the camera 101, for example, in the upper part of the camera 101, at a position corresponding to the face portion of the person 100 to be collated. Note that not only the guidance by display but also a voice guidance function may be added.

  The processing unit 104 inputs the face image from the camera 101, and uses the face image of the person obtained from the image input unit 105 to check the face, eyes, and nose using a pattern dictionary prepared in advance. A face detection unit 106 as a face detection unit for detecting the position of a facial part such as a feature extraction unit 107 as a feature extraction unit for extracting feature quantities such as grayscale information or partial space information based on the output of the face detection unit 106, At the time of registering dictionary information, dictionary information is stored as dictionary storage means for holding (registering) the feature amount extracted by the feature extraction unit 107 as recognition data (dictionary information) or holding dictionary information distributed from the outside. Unit 108, at the time of person verification (face verification), the feature amount (input feature information) extracted by the feature extraction unit 107 and the recognition data (registered in the dictionary information storage unit 108) Book information) to determine whether or not a predetermined relationship is established between the two information, for example, the similarity between the input feature information and the dictionary information is obtained, and the obtained similarity is higher than a threshold value The recognizing unit 109 as a verification unit that determines that the verification target person 100 is a registrant (person) and determines that it is an unregistered person (not the person) when the obtained similarity is lower than the threshold. The communication unit 110 includes a communication unit 110 for communicating with other person verification devices and entrance / exit control devices, and a control unit 111 serving as a control unit that performs overall control.

The image input unit 105 inputs the face image from the camera 101, digitizes it by A / D conversion, and sends it to the face detection unit 106.
First, the face detection unit 106 detects a face area of the person 100 to be collated from the face image input by the image input unit 105. For example, by obtaining a correlation value while moving a template prepared in advance in an image, a place having the highest correlation value is set as a face region. In addition, face detection means such as a face region extraction method using an eigenspace method or a subspace method may be used.

  Next, the face detection unit 106 detects the position of the facial parts such as eyes, nose, and mouth from the detected face area. The detection method is described in, for example, literature (Kazuhiro Fukui, Osamu Yamaguchi: “Face Feature Point Extraction by Combination of Shape Extraction and Pattern Matching”, IEICE Transactions (D), vol. J80-D-II, No. 8, pp2170-2177 (1997)).

  FIG. 3 shows an example of face detection results and eye / nose detection results. In FIG. 3, (fx, fy) is the center coordinates of the face, (fw, fh) is the size of the face, (EyeLx, EyeLy), (EyeRx, EyeRy) are the position coordinates of the left and right eyes, and (NoseLx, NoseLy). , (NoseRx, NoseRy) indicate the position coordinates of the left and right nostrils. The eye position indicates the center point of the black eye, and the nose position indicates the center point of the nostril.

  The feature extraction unit 107 cuts the face area into a certain size and shape based on the position of the face part detected by the face detection unit 106, and uses the shading information as a feature amount. Here, for example, the gray value of an area of m pixels × n pixels is used as information as it is, and m × n-dimensional information is used as a feature vector.

  Further, as will be described later, the partial space itself may be used as input data for recognition. Therefore, the result of calculating the partial space is sent to the recognition unit 109 and the dictionary information storage unit 108.

  The dictionary information storage unit 108 holds dictionary information such as a partial space (or correlation matrix) used for recognizing or identifying the person 100 to be verified. Also, attribute information such as date and time, time, and place at the time of registration can be held. The dictionary information is not limited to the partial space, and an input face image or an extracted face feature amount itself may be used.

  The recognizing unit 109 collates (compares) the recognition data (partial space) stored in the dictionary information storage unit 108 with the feature amount (shading information or partial space information) obtained by the feature extracting unit 107, thereby It recognizes who the person 100 to be collated who is photographing at 101 is identified, or identifies whether it is a corresponding person. In order to recognize a person, it suffices to determine which person's data is most similar, and the person corresponding to the data having the maximum similarity may be used as the recognition result.

  In addition, when performing facial recognition using a card, ID number, personal identification number, key, etc., the degree of similarity with recognition data corresponding to personal information such as each person's card or ID number is calculated. The threshold is set, and if the threshold is exceeded, the person is identified.

  Means for inputting such a card, an ID number, a personal identification number, a key, and the like are necessary. When an ID number or a password is used, key input means may be provided.

  As a recognition method, when information of the feature extraction unit 107 is used, a method such as a subspace method or a composite similarity method may be used. The recognition method in the present embodiment is, for example, a literature (Kenichi Maeda, Sadaichi Watanabe: “Pattern matching method introducing a local structure”, IEICE Transactions (D), vol. J68-D, No. 3, pp 345-352 (1985)), a mutual subspace method which is a known recognition method is used.

と対角化し、固有ベクトルΦｉｎを求める。２つのΦｉｎ、Φｄで表わされる部分空間の部分空間類似度（０．０〜１．０）を求め、それを認識するための類似度とする。 In this method, both the recognition data in the registration information stored in advance and the input data are expressed as partial spaces, and the “angle” formed by the two partial spaces is defined as the similarity. The subspace input here is referred to as an input subspace. Similarly, a correlation matrix Cin is obtained for the input data string,

And the eigenvector Φin is obtained. The subspace similarity (0.0 to 1.0) of the subspace represented by two Φin and Φd is obtained and used as the similarity for recognizing it.

  The recognition unit 109 operates as in the flowchart shown in FIG. First, the operation varies depending on whether recognition processing (one-to-one matching) or identification processing (one-to-one matching) is performed (step ST1). When performing the identification process, first, the ID number of the target person to be collated is read (step ST2). Next, registration information (dictionary information) corresponding to the target ID number is read from the dictionary information storage unit 108 (step ST3).

  Next, as described above, in order to perform recognition by the subspace method or the like, the similarity between the subspace of each registered information and the input vector (eigenvector from the feature extraction unit 107) or the input subspace is calculated. (Step ST4). Next, the similarity is compared with a preset threshold value (steps ST5 and ST6), and the identification result is output (step ST7).

  When performing recognition processing, all dictionary information to be collated is read from the dictionary information storage unit 108 (step ST8). Then, the similarity with each dictionary information is calculated (step ST9). Next, the maximum similarity is selected from the calculated similarities (step ST10), and is output as a recognition result (step ST12).

  Note that it is also possible to verify whether the recognition result is correct by determining the maximum similarity as a threshold value as in step ST11 surrounded by a broken line in FIG. 4 (step ST13). For example, when the degree of similarity is too low, it can be determined that it is not any recognition target.

Next, the basic operation of FIG. 1 in the above configuration will be briefly described.
In the following description, for example, the person verification device 11 is used as a registration device (biological registration device) for registering the face image of the person to be verified as dictionary information, and the other person verification devices 12, 13, and 14 are to be verified. Suppose that it is used as a collation device for collating a person's face image.

  First, the person verification device 11 as the registration device creates dictionary information of the verification target person 100 from the face image acquired by the camera 101 by the processing as described above. The created dictionary information is distributed via the network 15 to person verification devices 12, 13, and 14 as other verification devices.

  In the person collation devices 12, 13, and 14 as the collation devices, face collation of the person 100 to be collated is performed by the process as described above. That is, the dictionary information distributed from the person collation device 11 as the registration device is collated with the input feature information created from the face image acquired by the camera 101, and the similarity between the two is calculated. If the calculated similarity is equal to or greater than the set threshold value, the collation is successful, and if it is less than the threshold value, it is determined that the non-collation is successful.

  The verification results of the person verification devices 12, 13, and 14 are sent to the entrance / exit control devices 17, 18, and 19. The entrance / exit control devices 17, 18, 19 determine entrance / exit based on the collation results from the person collation devices 12, 13, 14 and the traffic area information from the entrance / exit management server 25, and the electric locks 22, 23, 24. Are controlled to open and close.

  That is, the entrance / exit control devices 17, 18, and 19 are notified of the results verified by the person verification devices 12, 13, and 14. The entrance / exit control devices 17, 18, 19 unlock the electric locks 22, 23, 24 if the face matching result is a successful matching and the verified person to be verified is a permitted person from the traffic area information. It is.

Next, the flow of the main processing centering on the initial dictionary information update processing will be described with reference to the flowchart shown in FIG.
First, in the person verification device 11 as a registration device, feature information is extracted from the face image of the verification target person (registrant) 100 acquired by the camera 101 to create dictionary information (step S1), and the created dictionary information And the ID number of the registrant are distributed to the person verification devices 12, 13, and 14 as other verification devices by the communication unit 110 via the network 15 (step S2).

  In the person collation devices 12, 13, and 14 as the collation devices, the dictionary information immediately after being distributed from the person collation device 11 is a one-to-one collation target person and not a one-to-N collation target person.

  In the person verification devices 12, 13, and 14, the ID number is input by the verification target person 100, and the dictionary information corresponding to the ID number input earlier in the dictionary information distributed from the person verification device 11 and the camera 101 are used. One-to-one matching is performed with the input feature information created from the face image acquired in (Steps S3 and S4).

If the collation is successful, the collation result is transmitted to the entrance / exit control devices 17, 18, 19 (step S5). If the one-to-one face verification fails (when the verification is not successful), the verification target person 100 is input a password (step S6). If the passwords are correct (step S7), The verification result is transmitted to the exit control devices 17, 18, and 19 (step S5).
If the passwords do not match in step S7, the process returns to step S3 and the same operation as described above is repeated.

  When the entry / exit control devices 17, 18, 19 receive the verification result, the verification target person 100 is allowed to pass through the access gate by referring to the traffic area information distributed from the entrance / exit management server 25. It is determined whether it has been performed, and the determination result is sent to the person verification devices 12, 13, and 14 (step S8).

When the person verification devices 12, 13, and 14 receive the determination result (step S9), if the determination result is a pass-permitted person (step S10), the face image acquired at the time of the face verification of the verification target person 100 is obtained. The dictionary information is used and updated (step S11).
In step S10, if the determination result is not a permitted person, the process returns to step S3 and the same operation as described above is repeated.
By performing such an initial dictionary update, differences in lighting environment and the like at the delivery destination can be absorbed, and the degree of similarity can be increased in the next face collation, and collation accuracy can be improved.

When the dictionary information update is completed, it is determined whether or not the initial dictionary update has been performed a predetermined number of times (step S12). It is assumed that the person is subject to 1-to-N verification.
In step S12, if the initial dictionary update has not been performed a predetermined number of times, the process returns to step S3 and the same operation as described above is repeated.

  As described above, if the person is not permitted to pass, the initial dictionary is not updated regardless of the success or failure of the face collation, so that the person is not a one-to-N collation target person. As a result, with respect to the registered number of people, the number of 1 to N verification target persons can be reduced for each person verification device, and the verification accuracy can be improved.

As described above, according to the above-described embodiment, when dictionary information is distributed to a person verification device that is different from the person verification device that has acquired (registered) dictionary information, the lighting environment of the distribution destination is captured. Therefore, it is possible to eliminate the influence due to the difference in lighting environment and improve the collation accuracy.
Further, by inquiring the room collation control device about the collation result of the person collation device, it is possible to narrow down the target person for 1 to N collation and improve the collation accuracy.

  In the above embodiment, a case has been described in which one of a plurality of person verification devices each having a registration and verification function is used as a registration device, and the remaining person verification devices are used as verification devices. However, it is not always necessary to do this, and for example, it may be configured by one person registration device dedicated for registration and a plurality of person verification devices dedicated for verification.

  In short, at least one biometric registration device for registering unique biometric information of the person to be collated as dictionary information and a location different from the biometric registration device, and via the communication line with the biometric registration device. And at least one biometric verification device that determines whether or not the verification target person is the person by verifying the input unique biometric information and the dictionary information distributed from the biometric registration device. What is necessary is just to be comprised.

The block diagram which shows roughly the structure of the entrance / exit management system to which the person collation system which concerns on embodiment of this invention is applied. The block diagram which shows the structure of a person collation apparatus roughly. The figure for demonstrating the process of a face detection part. The flowchart for demonstrating the flow of a process of a recognition part. The flowchart explaining the flow of the principal part process centering on the update process of initial dictionary information.

Explanation of symbols

  11, 12, 13, 14 ... person verification device (biometric verification device), 15 ... network (communication line), 16, 17, 18, 19 ... entry / exit control device, 21, 22, 23, 24 ... electric lock, 25 Entry / exit management server, 100 ... Person to be verified (person), 101 ... Camera (biological information acquisition unit), 102 ... Illumination unit (illumination unit), 103 ... Input / output unit (specific information acquisition unit), 104 ... Processing unit , 105 ... image input unit, 106 ... face detection unit, 107 ... feature extraction unit (feature extraction unit), 108 ... dictionary information storage unit (dictionary storage unit), 109 ... recognition unit (collation unit), 110 ... communication unit ( Communication means), 111... Control unit (control means).

Claims (8)

At least one biometric registration device for registering unique biometric information of the person to be collated as dictionary information, and the biometric registration device are installed at different locations and connected to the biometric registration device via a communication line. And at least one or more biometric verification devices that determine whether or not the person to be verified is the person himself / herself by collating the input unique biometric information with the dictionary information distributed from the biometric registration device. Configured
The biometric registration device
First specific information acquisition means for acquiring specific information for specifying a person to be verified;
First biological information acquisition means for acquiring unique biological information of the person to be verified;
Dictionary creating means for creating dictionary information from the biological information acquired by the first biological information acquiring means;
Distribution means for distributing the dictionary information created by the dictionary creating means to the biometric matching device together with the specific information acquired by the first specific information acquiring means;
The biometric matching device is:
Receiving means for receiving dictionary information and specific information distributed by the distribution means of the biometric registration device;
Dictionary storage means for storing the dictionary information and the specific information received by the receiving means in association with each other;
Second specific information acquisition means for acquiring specific information for specifying a person to be verified;
Second biological information acquisition means for acquiring unique biological information of the person to be verified;
By comparing the biometric information acquired by the second biometric information acquisition means with the dictionary information corresponding to the specific information acquired by the second specific information acquisition means stored in the dictionary storage means, Collating means for determining whether or not a predetermined relationship is established,
As a result of the collation by the collation means, when the collation succeeds when a predetermined relationship is established between the obtained biometric information and the dictionary information, the dictionary information stored in the dictionary storage means is obtained as the second biometric information acquisition. A person collation system comprising dictionary updating means for updating based on biometric information acquired by the means. The biometric matching device is:
As a result of the collation by the collation means, a password input means for inputting the password by the collation target person at the time of non-collation success when a predetermined relationship is not established between the acquired biometric information and the dictionary information;
Password confirmation means for confirming the success or failure of the password input by the password input means,
The dictionary updating means, when the password confirmation means confirms that the input password is correct, the dictionary information stored in the dictionary storage means, the biological information acquired by the second biological information acquisition means The person verification system according to claim 1, wherein the system is updated based on the information. The biometric matching device is:
Update number determination means for determining whether or not the dictionary information stored in the dictionary storage means by the dictionary update means has been updated a predetermined number of times;
When it is determined by the update count determination means that the dictionary information has been updated a predetermined number of times, the person to be collated is stored in the biometric information acquired by the second biometric information acquisition means and the dictionary storage means. 2. The person verification system according to claim 1, wherein the person verification system shifts to a 1-to-N verification target person for verification with all stored dictionary information. The biometric registration device
Collating means for judging whether or not a predetermined relationship is established between the two pieces of information by collating the biological information acquired by the first biological information acquiring means with the dictionary information created by the dictionary creating means. The person verification system according to claim 1, further comprising: At least one biometric registration device for registering unique biometric information of the person to be collated as dictionary information, and the biometric registration device are installed at different locations and connected to the biometric registration device via a communication line. One or more biometric matching devices that determine whether or not the person to be collated is a person by collating the input unique biometric information with dictionary information distributed from the biometric registration device, Connected to the verification device via a communication line, and configured to have an entrance / exit control device that controls opening / closing of the entrance / exit gate based on the verification result of the biometric verification device,
The biometric registration device
First specific information acquisition means for acquiring specific information for specifying a person to be verified;
First biological information acquisition means for acquiring unique biological information of the person to be verified;
Dictionary creating means for creating dictionary information from the biological information acquired by the first biological information acquiring means;
Distribution means for distributing the dictionary information created by the dictionary creating means to the biometric matching device together with the specific information acquired by the first specific information acquiring means;
The biometric matching device is:
First receiving means for receiving dictionary information and specific information distributed by the distribution means of the biometric registration device;
Dictionary storage means for storing the dictionary information and the specific information received by the first receiving means in association with each other;
Second specific information acquisition means for acquiring specific information for specifying a person to be verified;
Second biological information acquisition means for acquiring unique biological information of the person to be verified;
By comparing the biometric information acquired by the second biometric information acquisition means with the dictionary information corresponding to the specific information acquired by the second specific information acquisition means stored in the dictionary storage means, Collating means for determining whether or not a predetermined relationship is established,
As a result of the collation by the collation means, when the collation is successful when a predetermined relationship is established between the acquired biometric information and the dictionary information, the collation target person is a pass-permitted person who is permitted to pass to the pass gate. Inquiry means for making an inquiry as to whether there is an entry / exit control device,
The entrance / exit control device includes:
Passability information indicating whether or not the person to be verified is a pass-permitted person who is allowed to pass to the pass gate;
The verification target person is permitted to pass to the pass gate by referring to the passability information in response to an inquiry as to whether or not the verification target person from the inquiry means of the biometric matching device is a permitted person. Determination means for determining whether or not the person is permitted to pass;
Transmission means for transmitting the determination result of the determination means to the biometric matching device, the biometric matching device,
Second receiving means for receiving the determination result of the determining means transmitted by the transmitting means of the entrance / exit control device;
If the determination result received by the second receiving means is a passer, the dictionary information stored in the dictionary storage means is updated based on the biological information acquired by the second biological information acquiring means. An entry / exit management system further comprising a dictionary updating means. The biometric matching device is:
As a result of the collation by the collation means, a password input means for inputting the password by the collation target person at the time of non-collation success when a predetermined relationship is not established between the acquired biometric information and the dictionary information;
Password confirmation means for confirming the success or failure of the password input by the password input means,
The dictionary updating means, when the password confirmation means confirms that the input password is correct, the dictionary information stored in the dictionary storage means, the biological information acquired by the second biological information acquisition means The entrance / exit management system according to claim 5, wherein the entrance / exit management system is updated based on the above. The biometric matching device is:
Update number determination means for determining whether or not the dictionary information stored in the dictionary storage means by the dictionary update means has been updated a predetermined number of times;
When it is determined by the update count determination means that the dictionary information has been updated a predetermined number of times, the person to be collated is stored in the biometric information acquired by the second biometric information acquisition means and the dictionary storage means. 6. The entrance / exit management system according to claim 5, wherein the system shifts to a 1-to-N collation target person who collates all stored dictionary information. The biometric registration device
Collating means for judging whether or not a predetermined relationship is established between the two pieces of information by collating the biological information acquired by the first biological information acquiring means with the dictionary information created by the dictionary creating means. The entrance / exit management system according to claim 5, further comprising:

Images