JP2012014568A - Monitoring apparatus and method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the precision of authentication based on a face image.SOLUTION: A similarity computation section 232 computes, for collation, similarity between each of face images in a face image group of a person subjected to the collation captured by a face image capturing section 221 and a face image of an accumulation person accumulated in a biological information DB 22. A similarity computation result tabulation section 234 tabulates collation results of the face images in the face image group of the person subjected to the collation and generates similarity as a face image group of the person subjected to the collation. A person determination section 241 compares the similarity that is a tabulation result with a first threshold value to determine whether the face image of the person subjected to the collation is the face image of the accumulation person. In the case where the face image of the person subjected to the collation belongs to the accumulation person, if the similarity that is the tabulation result is higher than a second threshold value set higher than the first threshold value, a face image dictionary additional registration determination section 242 adds the face image of the person subjected to the collation as a face image of the accumulation person and additionally accumulates the face image of the person subjected to the collation to a database management section 225 as the face image of the accumulation person. The present invention may be applicable to a monitoring system.

Description

  The present invention relates to a monitoring apparatus, method, and program, and in particular, for biological information represented by a huge amount of face images stored in a database or the like, only highly reliable biological information is newly registered in the database. Thus, the present invention relates to a monitoring apparatus and method, and a program that can improve recognition accuracy based on biological information.

  Currently, in many stores and public facilities, authentication technology using facial images is used for security purposes and marketing research purposes (see Patent Document 1).

JP 2008-287658 A

  However, in Patent Document 1, there is a limit to the number of face images that can be stored. Therefore, even if face images of a large number of people can be actually acquired, they cannot be stored and cannot be stored. Even an image cannot be authenticated, and as the number of visitors or visitors increases, the number of face images that cannot be authenticated may increase.

  Further, in the technique of Patent Document 1, authentication processing is performed only by a person's face image at the time of visiting the store or at the time of visiting, and the sequentially acquired face images are not newly reflected in the database. The latest face image acquired could not be used effectively by prospering in the database.

  Therefore, by using the similarity between the acquired face image and all the face images registered in the database, it is authenticated whether or not it is the person by comparing with the threshold value, and the result is reflected in the database. It is possible. However, in the conventional authentication, since the threshold value used for comparison with the similarity is fixed, once the face image of the wrong authentication result is registered in the database, the authentication accuracy is lowered and the authentication accuracy is reduced. When the face image is authenticated in a lowered state, an erroneous authentication result is generated in a chain, and the incorrect face image is registered in a chain. Authentication accuracy may be reduced.

  The present invention has been made in view of such a situation, and in performing authentication processing based on biometric information represented by a face image, the degree of similarity with a registered face image is higher than the first threshold value. After being authenticated to be a high registered person, it is additionally registered as a new face image only when the similarity is higher than a second threshold set higher than the first threshold. By doing so, the authentication accuracy by the face image is improved.

  The monitoring device according to one aspect of the present invention includes an accumulation unit that accumulates a face image as an accumulator's face image in an accumulator database, an acquisition unit that acquires a plurality of face images of a collation target person as a face image group, and the acquisition The collation means for calculating and collating the similarity between each face image of the face image group of the collation target person acquired by the means and the face image of the accumulator accumulated in the accumulation means, and the face of the collation target person Aggregating means for generating the similarity as the face image group of the person to be collated by aggregating the collation results of each face image of the image group, the similarity as the aggregation result of the aggregating means and the first threshold value The similarity determination unit that determines whether or not the face image of the person to be collated is the face image of the accumulator, and the face image of the person to be collated is If the face image is determined, The face image of the person to be collated is added and accumulated as the face image of the accumulator by comparing the similarity that is the total result of the above and the second threshold value set higher than the first threshold value. An additional registration determination means for determining whether or not the face image of the person to be collated is added and stored as the face image of the person to be accumulated by the additional registration judgment means. Storage control means for controlling to add and store as a face image of the accumulator.

  The second threshold value can be set higher than the first threshold value and can be a value in a range where the stranger acceptance rate is zero.

  When the similarity determination unit does not determine that the face image of the person to be collated is the face image of the accumulator, the accumulation control unit performs control so that the face image of the person to be collated is newly accumulated. You can make it.

  When the similarity determination unit determines that the face image of the person to be collated is the face image of the accumulator, a notification unit for notifying that the person to be collated is the accumulator is further included. can do.

  The monitoring method according to one aspect of the present invention includes an accumulation unit that accumulates a face image as an accumulator's face image in an accumulator database, an acquisition unit that acquires a plurality of face images of a person to be collated as a face image group, and the acquisition The collation means for calculating and collating the similarity between each face image of the face image group of the collation target person acquired by the means and the face image of the accumulator accumulated in the accumulation means, and the face of the collation target person Aggregating means for generating the similarity as the face image group of the person to be collated by aggregating the collation results of each face image of the image group, the similarity as the aggregation result of the aggregating means and the first threshold value The similarity determination unit that determines whether or not the face image of the person to be collated is the face image of the accumulator, and the face image of the person to be collated is If the face image is determined, The face image of the person to be collated is added and accumulated as the face image of the accumulator by comparing the similarity that is the total result of the above and the second threshold value set higher than the first threshold value. An additional registration determination means for determining whether or not the face image of the person to be collated is added and stored as the face image of the person to be accumulated by the additional registration judgment means. In the monitoring method of the monitoring device including the accumulation control means for controlling to add and accumulate as the accumulator face image, the acquisition means acquires a plurality of face images of the person to be collated as a face image group. The degree of similarity between the acquisition step and each face image of the face image group of the person to be collated acquired by the process of the acquisition step in the collating unit and the face image of the accumulator accumulated in the accumulating unit is calculated. , A collation step, and a summarization step of generating a similarity as the face image group of the collation target person by summing the collation results of each face image of the face image group of the collation target person in the tabulation unit, Whether the face image of the person to be collated is the face image of the accumulator is determined by comparing the similarity that is the result of aggregation in the process of the aggregation step with the first threshold value in the similarity determination unit. When the similarity determination step for determination and the face image of the person to be collated are determined to be the face image of the accumulator by the processing of the similarity determination step in the additional registration determination means, the processing of the aggregation step The face image of the person to be collated is added and stored as the face image of the accumulator by comparing the similarity that is the result of the aggregation in Step 2 with the second threshold value that is set higher than the first threshold value. You An additional registration determination step for determining whether or not to add the facial image of the person to be collated as the facial image of the accumulator by the processing of the additional registration determination step in the storage control means A storage control step of performing control so that the face image of the person to be collated is added and stored as the face image of the accumulator.

  The program according to one aspect of the present invention includes an accumulating unit that accumulates a face image as an accumulator face image in an accumulator database, an acquisition unit that acquires a plurality of face images of a collation target person as a face image group, and the acquisition unit The collation means for calculating and collating the similarity between each face image of the face image group of the collation target person acquired by the above and the accumulator face image accumulated in the accumulation means, and the face image of the collation target person By summing up the collation results of each face image of the group, a summing unit that generates the similarity as the face image group of the person to be collated, a similarity that is the summing result of the summing unit, and a first threshold value Similarity determination means for determining whether the face image of the person to be collated is the face image of the accumulator by comparison, and the face image of the person to be collated is the face of the accumulator by the similarity determination means If it is determined that the image is an image, The face image of the person to be collated is added and stored as the face image of the accumulator by comparing the similarity that is the tabulation result with the second threshold value set higher than the first threshold value. An additional registration determination unit that determines whether or not to perform the check, and the additional registration determination unit determines that the face image of the person to be collated is to be added and accumulated as the face image of the person to be accumulated. A computer that controls a monitoring device that includes an accumulation control unit that performs control so that an image is added and accumulated as a face image of the accumulator, and a plurality of face images of the person to be collated in the acquisition unit as a face image group The degree of similarity between the acquisition step to be acquired, each face image of the face image group of the person to be verified acquired by the processing of the acquisition step in the verification unit, and the face image of the accumulator stored in the storage unit Total Then, a collation step for collation, and a tabulation for generating a similarity as the face image group of the collation target person by tabulating collation results of the face images of the collation target person's face image group in the tabulation unit Whether the face image of the person to be collated is the face image of the accumulator by comparing the similarity that is the result of aggregation in the process of the aggregation step in the similarity determination unit and the first threshold value. When the similarity determination step for determining whether or not the face image of the person to be collated is the face image of the accumulator by the processing of the similarity determination step in the additional registration determination unit, The face image of the person to be collated is added as the face image of the accumulator by comparing the similarity, which is the aggregation result in the processing of the step, with the second threshold value set higher than the first threshold value. Shi An additional registration determination step for determining whether or not to accumulate the image, and a determination that the face image of the person to be collated is added and accumulated as the face image of the accumulator by the process of the additional registration determination step in the accumulation control means. If so, a process including an accumulation control step of controlling to add and accumulate the face image of the person to be collated as the face image of the accumulator is executed.

  In one aspect of the present invention, a face image is accumulated as an accumulator face image in an accumulator database, a plurality of face images of a collation target person are acquired as a face image group, and the acquired collation target person face image group The degree of similarity between each face image and the stored accumulator face image is calculated and collated, and the collation results of each face image of the face image group of the collation target person are aggregated, whereby the collation The similarity as the face image group of the subject is generated, and whether or not the face image of the person to be collated is the face image of the accumulator is determined by comparing the similarity as the total result with the first threshold value. When it is determined and the face image of the person to be collated is determined to be the face image of the accumulator, the similarity that is the total result and a second threshold that is set higher than the first threshold By comparing the face image of the person to be collated with the face image of the accumulator. If it is determined whether to add and accumulate the face image of the person to be collated as the face image of the person to be accumulated, the face image of the person to be collated is It is controlled to be added and stored as a face image.

  In the monitoring device according to one aspect of the present invention, the accumulation unit that accumulates the face image as the accumulator's face image in the accumulator database is, for example, a biometric information database, and a plurality of face images of the person to be collated are stored in the face image group. The acquisition means acquired as, for example, is a face image acquisition unit, and each face image of the face image group of the verification target person acquired by the acquisition means, and the accumulator face image stored in the storage means, The matching means for calculating and matching the similarity is, for example, a similarity calculation unit, and by summing up the matching results of each face image of the face image group of the person to be collated, the face of the person to be collated The aggregation unit that generates the similarity as the image group is, for example, a similarity calculation result aggregation unit. By comparing the similarity that is the aggregation result of the aggregation unit with the first threshold, The facial image is the accumulator's facial image The similarity determination unit that determines whether or not the image is a person determination unit, for example, and the similarity determination unit determines that the face image of the person to be collated is the face image of the accumulator The face image of the person to be collated is added as the face image of the accumulator by comparing the similarity that is the total result of the totaling unit with a second threshold value that is set higher than the first threshold value. The additional registration determination means for determining whether or not to store the face image dictionary is, for example, a face image dictionary additional registration determination section, and the additional registration determination means uses the face image of the person to be collated as the face image of the accumulator. The accumulation control means for controlling to add and accumulate the face image of the person to be collated as the face image of the accumulator when it is determined to be additionally accumulated is, for example, a database management unit.

  In other words, the person determination unit, which is a similarity determination unit, obtains the acquired face image group by comparing the similarity of the face image group, which is the total result of the similarity between the face image group and the accumulator, with the first threshold value. It is determined whether or not the person is a person stored in the store database. When it is determined that the person in the face image group acquired by the person determination unit is a person stored in the accumulator database, the face image dictionary additional registration determination unit as additional registration determination means includes the face image group, When the similarity of the face image group is higher than the second threshold value by comparison with the second threshold value set higher than the first threshold value, the face image group is registered in addition to the accumulator database. I tried to make it.

  As a result, only when the degree of similarity between the face image group person and the accumulator face image exceeds a threshold value that is higher than the threshold value for determining whether or not the person is the same person, it is newly registered in the accumulator database. Therefore, it is possible to add only the face image with higher reliability in identifying the person and register it in the accumulator database.

  As a result, it is possible to improve the recognition accuracy of a person using a face image.

  According to the present invention, it is possible to improve the recognition accuracy of a person using a face image.

It is a figure which shows the structural example of one Embodiment of the monitoring system to which this invention is applied. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the camera of FIG. It is a figure which shows the example of installation of the entrance camera and shop camera of FIG. It is a figure explaining the structural example of the image processing unit of FIG. It is a figure explaining the structural example of the biometric information recognition apparatus of FIG. It is a flowchart explaining the monitoring process by the biometric information recognition apparatus of FIG. It is a flowchart explaining a person needing attention collation processing. It is a figure explaining a person-of-interest collation process. It is a figure explaining the 1st threshold and the 2nd threshold. And FIG. 11 is a diagram illustrating a configuration example of a general-purpose personal computer.

  Embodiments of the present invention will be described below. Correspondences between the configuration requirements of the present invention and the embodiments described in the detailed description of the present invention are exemplified as follows. This description is to confirm that the embodiments supporting the present invention are described in the detailed description of the invention. Accordingly, although there are embodiments that are described in the detailed description of the invention but are not described here as embodiments corresponding to the constituent elements of the present invention, It does not mean that the embodiment does not correspond to the configuration requirements. Conversely, even if an embodiment is described here as corresponding to a configuration requirement, that means that the embodiment does not correspond to a configuration requirement other than the configuration requirement. It's not something to do.

  That is, the monitoring device according to one aspect of the present invention includes a storage unit (for example, the biometric information DB 22 in FIG. 10) that stores a face image in the store database as a face image of the store, and a plurality of face images of the verification target person. Acquisition means (for example, the face image acquisition unit 221 in FIG. 10) acquired as a face image group, each face image of the face image group of the person to be collated acquired by the acquisition means, and the accumulation accumulated in the accumulation means By calculating the similarity with the person's face image and collating it (for example, the similarity calculating unit 232 in FIG. 10), and by summing up the result of collation of each face image of the face image group of the person to be collated The totaling means (for example, the similarity calculation result totaling unit 234 in FIG. 10) that generates the similarity as the face image group of the person to be collated, the similarity that is the totaling result of the totaling means, and the first threshold value Comparison of the person to be collated Similarity determination means (for example, the person determination unit 241 in FIG. 10) for determining whether the image is the face image of the accumulator, and the face image of the person to be collated is the accumulator by the similarity determination means. If it is determined that the face image is a face image of the person to be collated by comparing the similarity that is the totaling result of the totaling unit with a second threshold that is set higher than the first threshold Additional registration determination means (for example, a face image dictionary additional registration determination unit 242 in FIG. 10) for determining whether or not to add an image as the accumulator's face image and accumulate, and the additional registration determination means An accumulation control means for controlling to add and accumulate the face image of the person to be collated as the face image of the accumulator when it is determined that the person's face image is added and accumulated as the accumulator's face image For example, the database of FIG. Source management unit 225).

  When the similarity determination means determines that the face image of the person to be collated is the face image of the accumulator, notification means (for example, in FIG. 10) notifies that the person to be collated is the accumulator. A communication unit 223) can be further included.

  The monitoring method according to one aspect of the present invention includes an accumulation unit that accumulates a face image as an accumulator's face image in an accumulator database, an acquisition unit that acquires a plurality of face images of a person to be collated as a face image group, and the acquisition The collation means for calculating and collating the similarity between each face image of the face image group of the collation target person acquired by the means and the face image of the accumulator accumulated in the accumulation means, and the face of the collation target person Aggregating means for generating the similarity as the face image group of the person to be collated by aggregating the collation results of each face image of the image group, the similarity as the aggregation result of the aggregating means and the first threshold value The similarity determination unit that determines whether or not the face image of the person to be collated is the face image of the accumulator, and the face image of the person to be collated is If the face image is determined, The face image of the person to be collated is added and accumulated as the face image of the accumulator by comparing the similarity that is the total result of the above and the second threshold value set higher than the first threshold value. An additional registration determination means for determining whether or not the face image of the person to be collated is added and stored as the face image of the person to be accumulated by the additional registration judgment means. In the monitoring method of the monitoring device including the accumulation control means for controlling to add and accumulate as the accumulator face image, the acquisition means acquires a plurality of face images of the person to be collated as a face image group. The acquisition step (for example, step S11 in FIG. 11), each face image of the face image group of the person to be verified acquired by the processing of the acquisition step in the verification unit, and the storage stored in the storage unit A similarity step (for example, step S45 in FIG. 12) for calculating and comparing the similarity with the face image of the person to be collated, and a collation result of each face image of the face image group of the person to be collated in the aggregating means are aggregated. Thus, the summation step (for example, step S49 in FIG. 12) for generating the similarity as the face image group of the person to be collated and the similarity that is the summation result in the processing of the summation step in the similarity determination means A similarity determination step (for example, steps S15 and S20 in FIG. 11) for determining whether or not the face image of the person to be collated is the face image of the accumulator by comparing the degree and the first threshold; When the additional registration determination means determines that the face image of the person to be collated is the face image of the accumulator by the process of the similarity determination step, the aggregation result in the process of the aggregation step is determined. Whether or not the face image of the person to be collated is added and accumulated as the face image of the accumulator by comparing the similarity as a result with the second threshold value set higher than the first threshold value. The additional registration determination step (for example, steps S17 and S21 in FIG. 11), and the process of the additional registration determination step in the accumulation control unit, the face image of the person to be collated is used as the face image of the accumulator. An accumulation control step (for example, steps S18 and S22 in FIG. 11) for controlling to add and accumulate the face image of the person to be collated as the face image of the accumulator when it is determined to be additionally accumulated. Including.

[Example of monitoring system configuration]
FIG. 1 is a diagram showing a configuration of an embodiment of a game shop monitoring system according to the present invention.

  The game stores 1-1 to 1-n are so-called pachinko stores, pachislot stores, or casino stores. These amusement stores 1-1 to 1-n are affiliated stores or member stores of the biometric information management center or the third party amusement store management center, and stores that need to manage a plurality of stores in an integrated manner. It is. The game stores 1-1 to 1-n are connected by a biological information management bus 6 and a third-party game store management bus 7, and the public communication line networks 8 and 9 represented by the bus and the Internet are used. Via each other, biological information and third-party amusement store management information are exchanged. In the following description, when there is no particular need to distinguish each of the game stores 1-1 to 1-n, the game store 1 is simply referred to, and the other configurations are also referred to in the same manner.

  The biometric information management bus 6 mainly functions as a transmission path for distributing biometric information managed by the biometric information recognition device 21 of each game store 1. The third-party game store management bus 7 functions as a transmission path for distributing medium lending management information managed mainly by the medium lending management device 27 of each amusement store 1.

  The biometric information management center 2 is a server used by a business operator who manages and operates the biometric information management center. The registered player DB managed by the biometric information management database (hereinafter also referred to as DB) 3 is stored in the biometric information management center 2. In addition to updating based on the unregistered player DB generated by each gaming store 1, the updated updated registered player DB is distributed to the biometric information recognition device 21 of each gaming store 1.

  The third-party amusement store management center 4 is a server used by a business operator that manages and operates the third-party amusement store management center, and the medium lending management managed by the third-party amusement store management database (DB) 5 In addition to updating the information DB based on the information supplied from each game store 1, the updated latest medium lending management information is distributed to the medium lending management device 27 of each game store 1.

  The biometric information recognition apparatus 21 includes image processing units 39-1 to 39 based on images captured by the cameras 38-1 to 38-m, the entrance cameras 40-1 to 40-p, and the in-store cameras 41-1 to 41-q. Based on the face image information extracted by − (m + p + q) and supplied via the biometric information bus 31, the face image registered in advance in the biometric information database 22 is collated. The store visitor's visit is notified to the portable terminal 20 or displayed on the display unit 23 made up of an LCD (Liquid Crystal Display) or an organic EL (Electronic Luminescent). Further, when the face image registered in the biometric information database 22 is collated and does not match, the biometric information recognition device 21 registers the new biometric information in the biometric information DB 22.

  The game store management device 24 is a so-called hall computer, and monitors the operations of the game machines 36-1 to 36-m via the game store management information bus 30. The game store management device 24 determines a predetermined amount according to the monitoring status such as information on the payout of the game table 36 or the payout of medals, the call information of the players on the game tables 36-1 to 36-m, or the occurrence of an error. The above process is executed, and the execution result is displayed on the display unit 25 formed of an LCD, an organic EL, or the like. The game store management device 24 identifies information supplied from the counter 35, the game machines 36-1 to 36-m, and the game machine peripheral terminals 37-1 to 37-m, respectively. For example, it is managed by the gaming machine management database 26 in association with the gaming machine number.

  The medium lending management device 27 manages the medium lending management information of the rented game media using the medium lending management database 29 based on the information from the payment machine 33 and the lending machine 34, and also the medium lending management database. When the medium lending management information registered in 29 is updated, the updated information is sent to the third party amusement store management center 4 via the third party amusement store management bus 7 and the public communication line network 9. Further, the medium lending management device 27 acquires the medium lending management information supplied by the third party amusement store management center 4 via the third party amusement store management bus 7 and the public communication line network 9, and manages the medium lending management. Store in the database 29.

  The lending machine 34 lends a number of game media according to the amount when the player accepts a predetermined amount by cash or a prepaid card when playing on the gaming table 36. At this time, the lending machine 34 supplies information on the number of lent gaming media to the medium lending management device 27 together with information such as the accepted cash and the remaining number of prepaid cards. Thereby, the medium lending management device 27 registers information on the number of lent gaming media in the medium lending management information database 29 together with information such as the received cash and the remaining number of prepaid cards.

  The checkout machine 33 sells prepaid cards with a frequency for borrowing a ball. At this time, the checkout machine 33 supplies the medium lending management device 27 with the amount paid for the frequency of the prepaid card sold. Further, the settlement vending machine 33 settles and pays out cash based on the remaining number of game media lent as a frequency such as a prepaid card. At this time, the checkout machine 33 supplies the remaining number of prepaid cards and the amount of cash refunded to the medium lending management device 27.

  The counter 35 counts the number of game media acquired by the player playing on the game table 36, and outputs the counting result as a magnetic card or a receipt.

  The game machines 36-1 to 36-m execute a game when a predetermined operation is performed by the player, and pay out a game ball or a medal according to a so-called small hit or big hit.

  The game console peripheral terminals 37-1 to 37-m are so-called pedestrian machines provided corresponding to the respective game machines 36-1 to 36-m. The same as the lending machine 34) is provided. Further, the gaming machine peripheral terminal 37 acquires biological information such as a face image of the player who plays the gaming machine 36 and transmits it to the biological information recognition device 21 together with the gaming machine identification information (game machine number). FIG. 1 shows an example in which cameras 38-1 to 38-m that acquire a player's face image are provided as a function of acquiring biometric information.

  For example, as shown in FIG. 2, the cameras 38-1 to 38-m are arranged below the table display lamps 61-1 to 61-4 provided on the respective upper sides of the game tables 36-1 to 36-4. As shown in FIG. 3, a face image may be taken so that the player can take an image within the reading range δ. Can be used.

  Further, as shown in FIG. 4, the cameras 38-1 to 38-m are provided with convex portions 71-1 to 71-4 on the gaming machine peripheral terminals 37-1 to 37-4, as shown in FIG. As described above, it may be provided so that a player's face image can be captured within the reading range θ.

  Further, for example, as shown in FIG. 6, the cameras 38-1 to 38-m may be provided at the center of the game table 36 (on the board surface of the game table 36) to take an image. That is, by installing the camera 38 in the installation unit 81 of FIG. 6, the player is imaged within the reading range φ as shown in FIG.

  The entrance cameras 40-1 to 40-p and the in-store cameras 41-1 to 41-q are installed at entrances and predetermined places in the store of the amusement store 1, and imaged units 39- (m + 1) to 39- (m + p + q).

  The entrance cameras 40-1 to 40-p and the in-store cameras 41-1 to 41-q are set as shown in FIG. 8, for example. FIG. 8 shows an installation example of the entrance cameras 40-1 to 40-p and the in-store cameras 41-1 to 41-q in the game store 1.

  That is, in FIG. 8, entrances 112-1 to 112-3 are provided, and the entrance cameras 40-1 to 40-3 image players who enter the store from each entrance and exit 112. Further, the in-store cameras 41-1 to 41-10 are set at positions at which both surfaces of the island facilities 111-1 to 111-5 can be imaged in a row. The island facilities 111 are provided with game machines 36 on both sides, that is, so as to sandwich the island facilities 111 in the vertical direction in the figure. Since the camera 38, the entrance camera 40, and the in-store camera 41 all have a pan / tilt / zoom function, the in-store cameras 41-1 to 41-10 are arranged as shown in FIG. All players who play at 36 can take an image with any of the in-store cameras 41-1 to 41-10.

  Furthermore, the in-store camera 41-a is provided in front of the lending machine 34, the in-store camera 41-b is provided in front of the checkout machine 33, and the in-store camera 41-c is the counter of the counter 35. It is provided in front, and a player who uses the rental machine 34, the checkout machine 33, and the counter 35 can be imaged.

  That is, as shown in FIG. 8, in the game store 1, a player who visits the store, a player who plays on the game stand 36, and a player who uses the lending machine 34, the checkout machine 33, and the counter 35. The camera 38, the entrance camera 40, and the in-store camera 41 are installed so that almost all of the actions that the player is supposed to take in the gaming store 1 can be monitored.

[Configuration example of image processing unit]
Next, a configuration example of the image processing unit 39 will be described with reference to FIG.

  The image acquisition unit 201 acquires an image captured by the camera 38 (or the entrance camera 40 or the in-store camera 41) and supplies it to the face image extraction unit 202. The face image extraction unit 202 extracts a rectangular image made up of a face image from the image supplied from the image acquisition unit 201 using a pattern such as the arrangement of parts constituting the face, and supplies the extracted image to the person tracking unit 203. The person tracking unit 203 continuously tracks a rectangular image composed of face images, and supplies it to the transmitting unit 204 as a face image group composed of rectangular images that are continuously extracted by being tracked. The transmission unit 204 accumulates the face image continuously supplied from the face image extraction unit 202 in the buffer 204a, and when the supply of the face image is stopped, the transmission unit 204 displays the face image accumulated in the buffer 204a. It transmits to the biometric information recognition apparatus 21 as an image group. Since the capacity of the buffer 204a is limited, the transmitting unit 204 transmits a series of continuously supplied face images as a face image group when the capacity that can be stored in the buffer 204a is full. Alternatively, a predetermined number may be determined in advance, and when the predetermined number is accumulated, the predetermined number of face images may be transmitted as a face image group.

[Configuration example of biological information recognition apparatus]
Next, a configuration example of the biological information recognition device 21 will be described with reference to FIG.

  The face image acquisition unit 221 acquires a face image group including a plurality of face images supplied from the image processing unit 39 and supplies the face image group to the collation unit 222. The collation unit 222 includes the facial images of the facial image group acquired by the facial image acquisition unit 221, the sensitive person registration DB 22 a of the biological information DB 22, the sensitive persons registered in advance in the customer registration DB 22 b, and customer The face image is collated, and if there is a face image that is a candidate having a high degree of similarity, the candidate face image is displayed on the display unit 23 as a collation result, and is notified to the portable terminal 20 via the communication unit 223. The collation unit 222 supplies the supplied face image to the database registration management unit 225 when there is no face image that is a candidate with a high degree of similarity.

  More specifically, the feature amount extraction unit 231 of the collation unit 222 extracts a feature amount for identifying each face image in the face image group, and supplies the feature amount together with each face image to the similarity calculation unit 232. . The similarity calculation unit 232 extracts the feature amount of the face image of the person requiring attention or the customer registered in the customer registration DB 22a or the customer registration DB 22b of the biometric information DB 22, and from the feature amount extraction unit 231. The feature amount of each face image of the supplied face image group is used in order, and all the watched person registered in the biometric information DB 22 or the customer registration DB 22b or the face images of the customers. And is stored in the similarity calculation result storage unit 233 together with the face image supplied from the face image acquisition unit 221. More specifically, the similarity calculation unit 232, for example, based on various facial feature amounts such as the ratio between the distance between the eyes, the distance from the chin to the forehead, and the length from the chin to the nose, Each difference sum, average ratio, or ratio sum is obtained as the similarity.

  The similarity calculation result totaling unit 234 totals the calculation results of the similarity with the registered face image for each face image of the face image group stored in the similarity calculation result storage unit 233 to obtain a face image group. Is obtained and supplied to the similarity determination unit 235. More specifically, for example, the similarity calculation result accumulating unit 233 sets, for example, the similarity based on the face image having the highest similarity in the face image group as the similarity of the face image group, or An average value of similarities between all face images in the face image group and the registered face image is supplied to the similarity determination unit 235 as the similarity of the face image group.

  The person determination unit 241 of the similarity determination unit 235 accumulates the similarity supplied from the similarity calculation result totaling unit 234, and with the face image group that is the first among the similarities of the face image group. The similarity is compared with the first threshold, and based on the comparison result, the face image of the person requiring attention or the customer who becomes the first place is supplied to the face image group supplied from the face image acquisition unit 221. When similar (in the case of similarity indicating that the similarity is high, the similarity is high, when the similarity is higher than a predetermined threshold, or in the case of similarity indicating that the similarity is low, the similarity is low. When the information is lower than a predetermined threshold value, the information of the face image having the highest similarity is supplied to the display unit 23 and displayed, and the communication unit 223 and the face image dictionary additional registration determination unit 242 are also displayed. Supply. In addition, when the person determination unit 241 is not similar to the supplied face image group due to the comparison between the registered customer similarity and the first threshold, the face of the supplied customer is based on the comparison result. The image is supplied to the customer registration DB registration unit 252 and newly registered in the customer registration DB 22b. Furthermore, the face image dictionary additional registration determination unit 242 compares the similarity with the face image group that is ranked first and the second threshold value set higher than the first threshold value, and based on the comparison result, 1 If the similarity with the face image of the customer or the customer's face image is higher than the second threshold value, the face image group supplied from the face image acquisition unit 221 is registered in the database management unit 225 as the person requiring attention. The data are supplied to the DB registration unit 251 and the customer registration DB registration unit 252, and are additionally registered in the watched person registration DB 22a and the customer registration DB 22b, respectively.

  The operation unit 224 includes buttons, a mouse, a keyboard, and the like. The operation unit 224 is operated when any one of the face images displayed on the display unit 23 with the above-mentioned similarity ranked in the top three is selected. Is supplied to the communication unit 223. The communication unit 223 is configured with an Ethernet board or the like, and distributes the selected face image to the mobile terminal 20 based on an operation signal from the operation unit 224.

  Here, for example, the similarity indicates a higher value as it is closer to the face image registered as a registered player as indicated by the ratio sum, and the similarity is a value higher than a predetermined threshold value. In this case, an example will be described in which it is determined that the image is a person requiring attention corresponding to the similarity or a face image of a customer. However, for example, when the similarity is expressed as a sum of differences in the respective feature amounts of the captured face image and the face image registered as a customer or a customer, the similarity determination unit 235 displays the similarity. If the degree is smaller than the threshold value, the captured face image group is regarded as a face image of a person requiring attention or a customer, or in the case of an average ratio or the like, a predetermined value or more in the range of 0 to 1 And if it is a value close | similar to 1, it can be considered that it is the same person.

[Monitoring process]
Next, with reference to the flowchart of FIG. 11, the monitoring process by the face image by the biometric information recognition apparatus 21 of FIG. 10 is demonstrated.

  In step S <b> 1, the entrance camera 40 captures an image of the installed range and supplies the captured image to the image processing unit 39. The image acquisition unit 201 of the image processing unit 39 acquires the supplied image and supplies it to the face image extraction unit 202.

  In step S <b> 2, the face image extraction unit 202 extracts a player's face image from the supplied image, and supplies it to the person tracking unit 203. More specifically, the face image extraction unit 202 is, for example, a part of the captured image where the skin is exposed from a color scheme or the like, and the rectangular face is determined based on the arrangement of characteristic parts such as eyes and nose. An image is extracted and supplied to the person tracking unit 203.

  In step S3, the person tracking unit 203 searches the vicinity of the position where the rectangular face image is extracted by block matching, sequentially extracts the searched rectangular face images, and tracks the face image in the image. Then, the sequentially tracked rectangular face images are supplied to the buffer 204 a of the transmission unit 204.

  In step S4, the transmission unit 204 determines whether or not a predetermined time has elapsed. If the predetermined time has not elapsed, the process returns to step S1. That is, the processes in steps S1 to S4 are repeated until a predetermined time elapses, and a rectangular face image is sequentially extracted from the captured image while being sequentially tracked and stored in the buffer 204a of the transmission unit 204. .

  On the other hand, if it is determined in step S4 that the predetermined time has elapsed, in step S5, the transmission unit 204 uses the plurality of face images of the same person stored in the buffer 204a as a face image group as a biometric information recognition device. 21 and the process returns to step S1.

  In step S <b> 11, the face image acquisition unit 221 of the biological information recognition device 21 acquires a rectangular face image supplied from the image processing unit 39. As described above, since the capacity of the buffer 204a is limited, the face image may be extracted when the face image stored in the buffer 204a is full.

  In step S12, the face image acquisition unit 221 obtains the reliability of the face image of the supplied face image group. The reliability of the face image indicates a higher value as the face image is suitable for authentication using the face image, and is based on whether or not organ extraction such as eyes, nose, ears, or mouth has been performed. This is indicated by the total score set for each organ. That is, the more parts that can be extracted as organs used for face authentication, the higher the reliability. In addition, since the magnitude of the influence on the authentication accuracy varies from organ to organ, for example, a large weight is set for an organ that greatly affects the authentication accuracy such as the eyes and the mouth, and the other organs are small. A weight may be set.

  In step S <b> 13, the face image acquisition unit 221 extracts the face images up to the top n from the reliability of the acquired face image as a face image group, and supplies the face image group to the collation unit 222.

  In step S <b> 14, the collation unit 222 executes a person-of-interest collation process and is supplied from the face image that is biometric information registered in the person-of-care registration DB 22 a of the biometric information DB 22 and the face image acquisition unit 221. The similarity is obtained by comparing each face image of the top n face image groups.

  Here, with reference to the flowchart of FIG.

  In step S41, the feature amount extraction unit 231 sets an unprocessed face image among the supplied face image group as a processing target face image.

  In step S <b> 42, the feature amount extraction unit 231 extracts a feature amount from the processing target face image and supplies the feature amount to the similarity calculation unit 232.

  In step S <b> 43, the similarity calculation unit 232 determines the face of one unprocessed person of interest among the face images of the person registered as the person requiring attention registered in the person-of-care registration DB 22 a of the biometric information DB 22. An image is extracted and set as a processing target.

  In step S44, the similarity calculation unit 232 calculates the processing target face image supplied from the feature amount extraction unit 231 from the face image of the person of interest registered in the person-of-care registration DB 22a set as the process target. A feature quantity similar to the feature quantity is extracted.

  In step S45, the similarity calculation unit 232 determines the ratio of the eye-to-eye spacing, the length from the chin to the forehead, and the length from the chin to the nose for the face image supplied from the feature amount extraction unit 231. And the same feature amount in the face image of the watched person registered in the watchable person registration DB 22a of the biometric information DB 22, and the difference sum, the average ratio, or the sum of the ratios. Etc. are calculated as the similarity, and in step S46, the similarity that is the calculation result is supplied to and stored in the similarity calculation result storage unit 233.

  In step S47, the similarity calculation unit 232 determines whether or not an unprocessed face image of a person to be watched exists in the watched person registration DB 22a of the biometric information DB 22, and the face image of the unprocessed person to be watched is determined. If it exists, the process returns to step S43. In other words, the processes in steps S43 to S47 are repeated until the similarity with the face images of all the persons requiring attention in the person requiring attention DB 22a is calculated. If it is determined in step S47 that there is no unprocessed face image of the person to be watched in the watched person DB 22a, the process proceeds to step S48.

  In step S48, the feature amount extraction unit 231 determines whether there is a face image that is not a processing target face image in the extracted face image group, and a face image that is not a processing target face image. If it exists, the process returns to step S41. That is, until all the face images supplied as the face image group are set as the processing target face images and the similarity with the face images of the persons registered in the person-of-interest registration DB 22a is obtained, steps S41 to S41 are performed. The process of S48 is repeated.

  If it is determined in step S48 that there is no face image that is not a processing target face image in the extracted face image group, the process proceeds to step S49.

  In step S <b> 49, the similarity calculation result totaling unit 234 reads out and calculates the similarity calculation results stored in the similarity calculation result storage unit 233 and supplies the results to the similarity determination unit 235.

  In other words, for the face images up to the top n most highly reliable among the face images supplied from the face image acquisition unit 221 by the above processing, the persons requiring attention registered in the person-of-care registration DB 22a. The degree of similarity with the face image is obtained.

  Now, the description returns to the flowchart of FIG.

  In step S15, the person determination unit 241 of the similarity determination unit 235 has a similarity that is higher than the first threshold th1 based on the similarity count result. Then, it is determined whether or not the person is registered as a person requiring attention. That is, for example, when the top six face images with high reliability have been supplied and six caution persons are registered in the caution person registration DB 22a, for example, shown in the upper left part of FIG. Such a result is supplied as a result of the similarity score.

  That is, in FIG. 13, face images of attention person ID = 1 to 6 for identifying a person requiring attention are provided in the horizontal direction, and face images for identifying the face images having the highest reliability in the vertical direction. ID = 11 to 16 are provided, and the values on the respective matrices indicate the similarity. More specifically, (1, 11) (= (person ID requiring attention, face image ID)) is 880 points, (1, 12) is 900 points, and (1, 13) is 560 points. , (1,14) is 580 points, (1,15) is 570 points, and (1,16) is 580 points. Here, the similarity is indicated by 0 to 1000 points.

  Similarly, (2, 11) to (2, 16) are 900, 960, 570, 560, 580, and 570, respectively. In addition, (3, 11) to (3, 16) are 980, 860, 540, 550, 590, and 580, respectively. Further, (4, 11) to (4, 16) are 860, 880, 560, 580, 560, and 590, respectively. Further, (5, 11) to (5, 16) are 880, 880, 580, 580, 570, and 590, respectively. Further, (6, 11) to (6, 16) are 870, 870, 580, 590, 540, and 570, respectively.

  In other words, the person IDs 1 to 6 requiring attention are all front faces, and the face images in the face image group are face faces ID = 11 and 12 are front faces, but the other faces are downward. For this reason, among the face images of the face image group, the face image ID = 11 which is the front face is required to have the highest similarity.

  Here, the highest value as the similarity is (3, 11) (= (attention person ID, face image ID)) = 980, as shown in the white display portion at the upper left of FIG. If the first threshold value is 600, it is higher than the first threshold value. Therefore, the person of the face image to be collated is regarded as a person requiring attention, and the process proceeds to step S16.

  In step S <b> 16, the person determination unit 241 issues a report to indicate that a person requiring attention has visited the store. That is, for example, the person determination unit 241 displays an image indicating that a person requiring attention has visited the store on the display unit 23 and controls the communication unit 223 so that the person requiring attention has visited the mobile terminal 20. Announce that. Then, the person determination unit 241 records the time when the person requiring attention and the face image of the person requiring attention are recorded in a memory (not shown) and supplies the determination result to the face image dictionary additional registration determination unit 242. .

  In step S <b> 17, the face image dictionary additional registration determination unit 242 determines that the similarity is higher than the second threshold set higher than the first threshold th <b> 1 based on the result of the similarity calculation. It is determined whether the face image group that has been received is a face image to be registered as a face image of a person who needs attention. For example, in the upper left part of FIG. 13, the highest value as the similarity is (3, 1) (= (person required attention ID, face image ID)) = 980, and the second threshold is 800. Since it is higher than the second threshold value, it is considered that the face image group of the person of the face image to be collated should be registered as the face image of the person requiring attention, and the process proceeds to step S18.

  In step S18, the face image dictionary additional registration determination unit 242 instructs the database management unit 225 to add and register the current face image group to the watchable person registration DB 22a. In response to this, the database management unit 225 controls the watchable person registration DB registration unit 251 to additionally register the supplied face image group in the watchable person registration DB 22a of the biometric information DB 22.

  On the other hand, in step S15, for example, as shown in the lower left part of FIG. 13, all of the face image IDs = 21 to 26 of the current face image group are face images facing downward, and the maximum similarity is white. As indicated by the blank display portion, when the number is 590 points and does not exceed the first threshold value of 600 points, the processing of steps S16 to S18 is skipped. That is, in this case, it is regarded as not a face image of a person who needs attention.

  That is, since the face image ID = 11 to 16 shown in the upper left part of FIG. 13 has a maximum similarity value of 980 points higher than the second threshold value, the face image ID of the face image group = 11 to 16 Are registered in the watch-person registration DB 22a as shown in the lower right part of FIG. 13, for example. In the lower right part of FIG. 13, in addition to the face images of face image ID = 1 to 6, face images of face image ID = 11 to 16 of the face image group shown in the upper left part of FIG. 13 are additionally registered. It has been shown that

  As a result, when information on the face image group of the same person as the face image of the person to be watched registered in the watched person registration DB 22a is supplied as in the prior art, the watch-to-watch person registration DB 22a remains unupdated. Then, for example, as shown in the lower left part of FIG. 13, when face image IDs = 21 to 26 of the face image group just facing downward are supplied, the similarity does not exceed even the first threshold, A person who needs attention cannot be detected simply because all face images face downward.

  On the other hand, as described above, in the case of a face image group including a face image having a similarity higher than the second threshold, registration of the face image of the face image group provides high reliability. A highly reliable downward face image is registered together with the front face. That is, as shown in the lower right part of FIG. 13, in addition to the face image IDs 1 to 6 that have been registered in the watched person registration DB 22a until now, the face image ID of the front face with high reliability is set to 11 and 12 downward. The face images with face image ID = 13 to 16 are also registered. As a result, even if the face image ID is downward 21 to 26, since a face image that faces downward is newly registered as a person to be watched, as shown in the white display portion in the lower right part of FIG. The maximum value of the similarity is 980 points, and it can be recognized as a face image of a registered person requiring attention. As a result, it is possible to improve the authentication accuracy in the authentication process using the face image.

  In step S <b> 19, the collation unit 222 executes customer registration person collation processing, and the face image, which is biometric information registered in the customer registration DB 22 b of the biometric information DB 22, and the host image supplied from the face image acquisition unit 221. The respective face images in the face image group up to the n-th place are collated to find their similarity. As for the customer registered person matching process, the similarity between each face image of the face image group in the watched person matching process and the face image of the watched person registered in the watched person registration DB 22a of the biometric information DB 22 is obtained. The description is omitted because it is the same as the person-of-interest matching process except that the similarity with the face image of the person who is the customer registered in the customer registration DB 22b is obtained instead of the process.

  In step S <b> 20, the person determination unit 241 of the similarity determination unit 235 has a similarity higher than the first threshold th <b> 1 based on the result of the similarity calculation. It is determined whether or not the person is registered as a person who is a customer.

  If it is determined in step S20 that the person is registered as a customer, the person determination unit 241 notifies the determination result to the face image dictionary additional registration determination unit 242, and the process proceeds to step S21.

  In step S <b> 21, the face image dictionary additional registration determination unit 242 determines that the similarity is higher than the second threshold set higher than the first threshold th <b> 1 based on the similarity summation result. It is determined whether the face image group that has been added is a face image to be added and registered as a customer face image. For example, if the face image group of persons of the collation target face image is considered to be added and registered as the customer's face image, the process proceeds to step S22.

  In step S22, the face image dictionary additional registration determination unit 242 instructs the database management unit 225 to add and register the current face image group to the customer registration DB 22b. In response to this, the database management unit 225 controls the customer registration DB registration unit 252 to additionally register the supplied face image group in the customer registration DB 22b of the biometric information DB 22.

  In step S23, the person determination unit 241 records the time when the customer visited the store, the face image of the customer, and the like in a memory (not shown).

  In step S21, for example, if any similarity does not exceed the second threshold value of 800 points, the process of step S22 is skipped, and the process proceeds to step S23.

  Furthermore, in step S20, for example, as shown in the lower left part of FIG. 13, all of the face images of the current face image group are downward face images, and any similarity is the first threshold value. If not exceeding 600 points, the process proceeds to step S24.

  In step S24, the person determination unit 241 records the time when the customer visited the store, the face image of the customer, and the like in a memory (not shown).

  In step S25, the person determination unit 241 instructs the database management unit 225 to newly register the current face image group to the customer registration DB 22b. In response to this, the database management unit 225 controls the customer registration DB registration unit 252 to newly register the supplied face image group in the customer registration DB 22b of the biometric information DB 22.

  As described above, also in the customer registration DB 22b, it is possible to improve the recognition accuracy in the authentication process for the face image, as in the case of the face image of the person in the watched person DB 22a described above.

  In addition, regarding the first threshold and the second threshold, the relationship between the person rejection rate (FRR) and the other person acceptance rate (FAR), which mistakes the person for others, and the point indicating similarity (1000 points) is as follows: It is shown in FIG. That is, the principal rejection rate (FRR) increases as the similarity increases, and conversely, the other person acceptance rate (FAR) increases as the similarity decreases. For this reason, in the case of FIG. 14, the first threshold th1 is set to about 600 points where the principal rejection rate (FRR) is guaranteed to some extent, and the second threshold th2 is set to be the other person acceptance rate (FAR). You may make it set to about 800 points used as the range which can guarantee zero.

  According to the above, when the similarity between the registered face image and the face image of the face image group to be collated is obtained, the second threshold value is set higher than the first threshold value that is recognized as a match. By registering additional face images of the face image group to be collated when they are high, it becomes possible to register face images with high reliability as similarity, and similarities due to different face orientations, etc. Is low, but because it is a face image of the same face image group that is being tracked, it is guaranteed that the person is the same person. Recognition accuracy can be improved even if the face orientation of the target face image group changes.

  Incidentally, the series of monitoring processes described above can be executed by hardware, but can also be executed by software. When a series of processing is executed by software, a program constituting the software may execute various functions by installing a computer incorporated in dedicated hardware or various programs. For example, it is installed from a recording medium in a general-purpose personal computer or the like.

  FIG. 15 shows a configuration example of a general-purpose personal computer. This personal computer incorporates a CPU (Central Processing Unit) 1001. An input / output interface 1005 is connected to the CPU 1001 via the bus 1004. A ROM (Read Only Memory) 302 and a RAM (Random Access Memory) 1003 are connected to the bus 1004.

  An input / output interface 1005 includes an input unit 1006 including an input device such as a keyboard and a mouse for a user to input an operation command, an output unit 1007 for outputting a processing operation screen and an image of a processing result to a display device, a program and various data A storage unit 1008 including a hard disk drive for storing data, a LAN (Local Area Network) adapter, and the like, and a communication unit 1009 for performing communication processing via a network represented by the Internet are connected. Also, a magnetic disk (including a flexible disk), an optical disk (including a CD-ROM (Compact Disc-Read Only Memory), a DVD (Digital Versatile Disc)), a magneto-optical disk (including an MD (Mini Disc)), or a semiconductor A drive 1010 for reading / writing data from / to a removable medium 1011 such as a memory is connected.

  The CPU 1001 is read from a program stored in the ROM 1002 or a removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, installed in the storage unit 1008, and loaded from the storage unit 1008 to the RAM 303. Various processes are executed according to the program. The RAM 1003 also appropriately stores data necessary for the CPU 1001 to execute various processes.

  In this specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in time series in the order described, but of course, it is not necessarily performed in time series. Or the process performed separately is included.

  Further, in this specification, the system represents the entire apparatus constituted by a plurality of apparatuses.

1, 1-1 to 1-n amusement store 2 biometric information management center 3 biometric information management database 4 third party amusement store management center 5 third party amusement store management database 6 biometric information management bus 7 third party amusement store management bus 8, 9 Public communication network 21 Biometric information recognition device 22 Biometric information database 24 Game store management device 26 Game table management database 27 Medium lending management device 29 Medium lending management database 30 Amusement store management information bus 31 Biometric information bus 33 Settling machine 34 Lending machine 35 Counter 36,36-1 thru 36-m Game stand 37,37-1 thru 37-m Game stand peripheral terminal 38,38-1 thru 38-m Camera 39,39-1 thru 39- (m + p + q) Image processing unit 40, 40-1 to 40-p Entrance camera 41, 41-1 to 41-q In-store camera

Claims (6)

Accumulation means for accumulating a face image as an accumulator face image in an accumulator database;
Acquisition means for acquiring a plurality of face images of a person to be collated as a face image group;
Collation means for calculating and collating the similarity between each face image of the face image group of the person to be collated acquired by the acquisition means and the face image of the accumulator accumulated in the accumulation means;
Aggregating means for generating similarity as the face image group of the person to be collated by totaling the collation results of the face images of the face image group of the person to be collated;
Similarity determination means for determining whether or not the face image of the person to be collated is the face image of the accumulator by comparing the similarity that is the aggregation result of the aggregation means and a first threshold value;
When the similarity determination unit determines that the face image of the person to be collated is the face image of the accumulator, it is set higher than the similarity that is the counting result of the counting unit and the first threshold value. Additional registration determination means for determining whether to add and store the face image of the person to be collated as the face image of the accumulator by comparison with the second threshold value,
When it is determined by the additional registration determination means that the face image of the person to be collated is added and accumulated as the face image of the accumulator, the face image of the person to be collated is added and accumulated as the face image of the accumulator. And a storage control means for controlling the monitoring device. The monitoring apparatus according to claim 1, wherein the second threshold value is set to be higher than the first threshold value, and is a value in a range where the stranger acceptance rate is zero. If the similarity determination means does not determine that the face image of the person to be collated is the face image of the person to be accumulated, the accumulation control means controls to newly accumulate the face image of the person to be collated The monitoring apparatus according to claim 1. 2. The information processing apparatus according to claim 1, further comprising a notification unit that notifies that the collation target person is the accumulator when the similarity determination unit determines that the face image of the collation target person is the face image of the accumulator. The monitoring device described in 1. Accumulation means for accumulating a face image as an accumulator face image in an accumulator database;
Acquisition means for acquiring a plurality of face images of a person to be collated as a face image group;
Collation means for calculating and collating the similarity between each face image of the face image group of the person to be collated acquired by the acquisition means and the face image of the accumulator accumulated in the accumulation means;
Aggregating means for generating similarity as the face image group of the person to be collated by totaling the collation results of the face images of the face image group of the person to be collated;
Similarity determination means for determining whether or not the face image of the person to be collated is the face image of the accumulator by comparing the similarity that is the aggregation result of the aggregation means and a first threshold value;
When the similarity determination unit determines that the face image of the person to be collated is the face image of the accumulator, it is set higher than the similarity that is the counting result of the counting unit and the first threshold value. Additional registration determination means for determining whether to add and store the face image of the person to be collated as the face image of the accumulator by comparison with the second threshold value,
When it is determined by the additional registration determination means that the face image of the person to be collated is added and accumulated as the face image of the accumulator, the face image of the person to be collated is added and accumulated as the face image of the accumulator. In the monitoring method of the monitoring device including the storage control means for controlling to
An acquisition step of acquiring a plurality of face images of the person to be collated as a face image group in the acquisition means;
Collation for calculating and collating the similarity between each face image of the face image group of the person to be collated acquired by the process of the obtaining step in the collating means and the face image of the accumulating person accumulated in the accumulating means Steps,
A totaling step of generating a similarity as the face image group of the collation target person by totalizing collation results of the face images of the face image group of the collation target person in the tabulation unit;
Whether the face image of the person to be collated is the face image of the accumulator is determined by comparing the similarity that is the result of aggregation in the process of the aggregation step with the first threshold value in the similarity determination unit. A similarity determination step for determining;
In the additional registration determination unit, when it is determined that the face image of the person to be collated is the face image of the accumulator by the process of the similarity determination step, the similarity that is a total result in the process of the totaling step And whether to add and store the face image of the person to be collated as the face image of the accumulator by comparison with a second threshold value set higher than the first threshold value. A registration determination step;
If it is determined in the accumulation control means that the face image of the person to be collated is added and accumulated as the face image of the person to be accumulated by the process of the additional registration determination step, the face image of the person to be collated is stored in the person to be accumulated An accumulation control step for controlling to add and accumulate as a face image of the image. Accumulation means for accumulating a face image as an accumulator face image in an accumulator database;
Acquisition means for acquiring a plurality of face images of a person to be collated as a face image group;
Collation means for calculating and collating the similarity between each face image of the face image group of the person to be collated acquired by the acquisition means and the face image of the accumulator accumulated in the accumulation means;
Aggregating means for generating similarity as the face image group of the person to be collated by totaling the collation results of the face images of the face image group of the person to be collated;
Similarity determination means for determining whether or not the face image of the person to be collated is the face image of the accumulator by comparing the similarity that is the aggregation result of the aggregation means and a first threshold value;
When the similarity determination unit determines that the face image of the person to be collated is the face image of the accumulator, it is set higher than the similarity that is the counting result of the counting unit and the first threshold value. Additional registration determination means for determining whether to add and store the face image of the person to be collated as the face image of the accumulator by comparison with the second threshold value,
When it is determined by the additional registration determination means that the face image of the person to be collated is added and accumulated as the face image of the accumulator, the face image of the person to be collated is added and accumulated as the face image of the accumulator. A computer that controls a monitoring device including storage control means for controlling
An acquisition step of acquiring a plurality of face images of the person to be collated as a face image group in the acquisition means;
Collation for calculating and collating the similarity between each face image of the face image group of the person to be collated acquired by the process of the obtaining step in the collating means and the face image of the accumulating person accumulated in the accumulating means Steps,
A totaling step of generating a similarity as the face image group of the collation target person by totalizing collation results of the face images of the face image group of the collation target person in the tabulation unit;
Whether the face image of the person to be collated is the face image of the accumulator is determined by comparing the similarity that is the result of aggregation in the process of the aggregation step with the first threshold value in the similarity determination unit. A similarity determination step for determining;
In the additional registration determination unit, when it is determined that the face image of the person to be collated is the face image of the accumulator by the process of the similarity determination step, the similarity that is a total result in the process of the totaling step And whether to add and store the face image of the person to be collated as the face image of the accumulator by comparison with a second threshold value set higher than the first threshold value. A registration determination step;
When it is determined in the accumulation control means that the face image of the person to be collated is added and accumulated as the face image of the person to be accumulated by the process of the additional registration determining step, the face image of the person to be collated is A storage control step for performing control so as to be added and stored as a face image.

Images