JP5013172B2 - Information processing apparatus and method, and program - Google Patents

Description

  The present invention relates to an information processing apparatus, method, and program, and more particularly, to an information processing apparatus, method, and program that can realize management and analysis of customer visit information at higher speed with higher accuracy.

  Information such as searchers taken up in the media is often based on gender, age, height, and clothing. For this reason, as a method of matching a person, the person is often matched based on the facial feature points, and attribute elements of gender and age are often added.

  However, matching and attribute elements are independent, and it is possible to extract persons with clearly different attributes by extracting only matching results from facial feature points without referring to attributes during matching. Yes, it seemed to impair trust.

  Therefore, it is possible to capture gender, age, etc. from individual images as elements to be added to the collation, but there is no established method for estimating the height that is often included in the clues, and various methods Has been proposed.

  For example, in order to estimate the height, there has been proposed one in which a plurality of cameras (imaging means) are installed and the height is estimated based on a plurality of imaging results (see Patent Document 1). In addition, there has been proposed one that estimates a height by changing a range of imaging by controlling a camera (imaging means) (see Patent Document 2).

JP 2002-183734 A

JP 2002-278940 A

  However, in the above example, the cost increases due to the increase in the number of installed cameras, and the processing time required to change the imaging range by controlling the camera is required, so the height is estimated at low cost at high speed. I couldn't.

  The present invention has been made in view of such a situation, and makes it possible to estimate the height at high speed at low cost, and to manage customer visit information at high speed with high accuracy.

An information processing apparatus according to an aspect of the present invention extracts an image capturing unit that captures an image of a predetermined range at an entrance of a game store, and a feature amount of a face image of a person to be collated on the image captured by the image capturing unit. And an attribute code set by a table made of any one of a plurality of attribute information or a combination of them on the image captured by the imaging unit. Among the estimation means, the accumulation means for accumulating face images of registrants registered in advance in association with the attribute codes, and the estimation among the registrants accumulated in the accumulation means in association with the attribute codes. a registrant extraction means and the face image of the registrant has been extracted by the extraction means registrants for extracting registrants having the attribute code estimated by means, the collation object person Collation with a face image based on the feature quantity of the face image, collation determination means for determining whether or not the person to be collated is the registrant, and the person to be collated is registered by the collation determination means Notification means for notifying that the person to be collated is the registrant.

Wherein the plurality of attribute information, height, age, and gender can be Rukoto as to include.

  The attribute estimation unit may include a position acquisition unit that acquires a position of a face image of a predetermined size of the person to be collated on the image captured by the imaging unit. The height of the person of the face image can be estimated based on the position of the face image of a predetermined size of the person to be collated on the image acquired by the means.

  The attribute estimation unit can estimate the age based on the feature amount extracted by the feature amount extraction unit.

  The attribute estimation unit can estimate the sex based on the feature amount extracted by the feature amount extraction unit.

An acquisition means for acquiring a face image satisfying a predetermined search condition from the face image stored in the storage means, and a face image for extracting a reference face image and a non-reference face image from the face images acquired by the acquisition means Of the non-reference face image, an extraction means, a reference face image feature quantity extraction means for extracting a feature quantity of the reference face image , a non-reference face image attribute estimation means for estimating an attribute code of the non -reference face image, Corresponding attribute non-reference face image extraction means for extracting only the non-reference face image having the attribute code estimated by the non-reference face image attribute estimation means, and the non-reference face image extraction means extracted by the corresponding attribute non-reference face image extraction means. Similarity determination means for comparing a reference face image with the reference face image based on a feature amount of the face image and determining whether the non-reference face image is similar to the reference face image; Similarity determination If the step determines that the non-reference face image is similar to the reference face image, group registration means for registering the non-reference face image as a group of the reference face images is further included. Can do.

An information processing method according to one aspect of the present invention includes an imaging step of capturing an image of a predetermined range at an entrance of a game store, and a feature amount of a face image of a person to be collated on the image captured by the processing of the imaging step And an attribute set by a table made of any one of a plurality of attribute information or a combination of them on the image captured by the process of the imaging step an attribute estimation step of estimating a code in advance the face image of the registered subscribers and storing step of storing in association with the attribute code, registered accumulated in association with the attribute code in the processing of the storage step of's and registrant extracting a registrant with an attribute code estimated by the processing of said estimating step, said Noboru The face image of the registrant extracted by the process of the person extracting step and the face image of the person to be collated are collated based on the feature amount of the face image, and whether or not the person to be collated is the registrant. A matching determination step for determining whether or not the facial image of the registrant registered in advance by the processing of the storage step, and the facial image of the verification target person, the feature amount of the facial image and the attribute estimation Collation based on the attribute estimated by the processing of the step, collation determination step for determining whether or not the verification target person is the registrant, and the verification target person is the registrant by the processing of the verification determination step A notification step for notifying that the person to be collated is the registrant.

The program according to one aspect of the present invention extracts an image capturing step of capturing an image of a predetermined range at an entrance of a game store, and a feature amount of the face image of the person to be collated on the image captured by the processing of the image capturing step. And an attribute code set by a table made of any of a plurality of attribute information of the verification target person or a combination thereof on the image captured by the processing of the feature extraction step and the imaging step An attribute estimation step to be estimated, a storage step of storing a pre-registered registrant's face image in association with the attribute code, and a process of the storage step of the registrant stored in association with the attribute code among the registrant extracting a registrant with an attribute code estimated by the processing of said estimating step, the registration The face image of the registrant extracted by the processing of the extraction step and the face image of the person to be collated are collated based on the feature amount of the face image, and whether or not the person to be collated is the registrant. And a notifying step for notifying that the verification target person is the registrant when the verification target person is determined to be the registrant by the processing of the verification determination step. Have the computer execute the process.

An information processing apparatus according to an aspect of the present invention captures an image in a predetermined range, extracts a feature amount of a face image of a person to be collated on the captured image, and performs the collation on the captured image. A target person's attribute code set by any one of a plurality of attribute information or a combination thereof is estimated, and a pre-registered registrant's face image is stored in association with the attribute code , Among the registrants stored in association with the attribute code , the registrant with the estimated attribute code is extracted, and the extracted registrant face image and the face image of the collation target person are: Based on the feature amount of the face image, it is determined whether or not the verification target person is the registrant, whether or not the verification target person is the registrant, and the verification target person Is the registrant If it is determined that that, said collation object person is the registrant is notified.

In the information processing apparatus according to one aspect of the present invention, the imaging unit that captures an image of a predetermined range at the entrance of a game shop is, for example, an entrance camera, and the verification target person on the image captured by the imaging unit The feature quantity extraction means for extracting the feature quantity of the face image is, for example, a feature quantity extraction unit, and one of a plurality of attribute information of the person to be collated on the image captured by the imaging means , or Attribute estimation means for estimating an attribute code set by a table composed of a combination thereof Height estimation section or attribute estimation section, and storage means for storing a pre-registered registrant's face image in association with the attribute code genus, for example, a biological information DB, which among the registrants are stored in association with the attribute code in the storage means, estimated by the estimating means Registrant extraction means for extracting a registrant with the code, for example, an extraction unit, and the registrant's face image extracted by the registrant extracting means and facial image of the collation object person, the face The collation determination unit that collates based on the feature amount of the image and determines whether or not the collation target person is the registrant is, for example, a similarity determination unit. When it is determined that the person is the registrant, the notification unit that notifies that the person to be collated is the registrant is, for example, a communication unit.

That is, the similarity determination unit collates the face image of the registrant stored in the biometric information DB with the face image of the person to be collated based on the feature amount of the face image, and the person to be collated Before determining whether or not the user is a registrant, the extraction unit selects a registrant with the attribute estimated by the height estimation unit, that is, the height condition, among the registrants stored in the biological information DB. Since extraction is performed, it is determined whether or not the person to be collated is the registrant based on the feature amount of only the registrant who has the attribute having the height condition in advance and the collator. will be determination process is omitted, both the verification process makes it possible to speed, it becomes possible to improve collation accuracy.

As a result, both becomes possible to estimate the height at a high speed at low cost, it is possible to manage customer visit information at high speed with high accuracy.

According to the present invention, both becomes possible to estimate the height at a high speed at low cost, it is possible to manage customer visit information at high speed with high accuracy.

  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, an information processing apparatus according to an aspect of the present invention includes an imaging unit that captures an image in a predetermined range at an entrance of a game store (for example, the entrance camera 42 in FIG. 11) and an image captured by the imaging unit. A feature amount extraction unit (for example, the feature amount extraction unit 231 in FIG. 11) that extracts a feature amount of the face image of the person to be collated, and a plurality of the person to be collated on the image captured by the image capturing unit. Attribute estimation means (for example, the height estimation unit 212b in FIG. 10 or the attribute estimation unit 232 in FIG. 11) for estimating an attribute code set by a table comprising any one of these attribute information or a combination thereof, and registered in advance has been storing means the registrant's face image storing in association with the attribute code (e.g., biological information DB22 in FIG. 11) and the attribute code in association with registrant stored in the storage means Chi, the registrant extraction means for extracting a registrant with an attribute code estimated by the estimation means (e.g., the extraction unit 233 of FIG. 11), a face image of the registrant extracted by the registrant extracting means Collation determination means for collating the face image of the person to be collated based on the feature amount of the face image and determining whether or not the person to be collated is the registrant (for example, the similarity in FIG. 11) And a notification unit (for example, the communication in FIG. 11) that notifies that the verification target person is the registrant when the verification target unit determines that the verification target person is the registrant. Part 224).

  The attribute estimation unit (for example, the height estimation unit 212b in FIG. 10) includes a position acquisition unit (for example, a position of a face image of a predetermined size of the person to be collated on the image captured by the imaging unit (for example, , Based on the position of a face image of a predetermined size of the person to be collated on the image acquired by the position acquisition means. Thus, the height of the person of the face image can be estimated.

  The attribute estimation unit (for example, the age estimation unit 232a of the attribute estimation unit 232 in FIG. 11) may be configured to estimate the age based on the feature amount extracted by the feature amount extraction unit.

  The attribute estimation unit (for example, the gender estimation unit 232b of the attribute estimation unit 232 in FIG. 11) may be configured to estimate the gender based on the feature amount extracted by the feature amount extraction unit.

An acquisition unit (for example, the face image acquisition unit 331 in FIG. 21) that acquires a face image satisfying a predetermined search condition from the face image stored in the storage unit (for example, the biometric information DB 22 in FIG. 21), and the acquisition unit of the obtained face image, the face image extracting means for extracting the reference face image and a non-reference face image (for example, the feature extraction unit 333 of FIG. 21), a reference face for extracting a feature value of the reference face image Image feature quantity extraction means (for example, feature quantity extraction section 333 in FIG. 21) and non-reference face image attribute estimation means (for example, age estimation section 334 in FIG. 21 or gender estimation) that estimates the attribute code of the non-reference face image Unit 335) and corresponding attribute non-reference face image extraction means (for example, FIG. 5) for extracting only non-reference face images having the attribute code estimated by the non-reference face image attribute estimation means from among the non-reference face images . 21 extraction units 336) and the corresponding attribute non-reference face The non-reference face image extracted by the image extraction means and the reference face image are collated based on the feature amount of the face image, and it is determined whether or not the non-reference face image is similar to the reference face image. When the similarity determination unit (for example, the similarity determination unit 339 in FIG. 21) and the similarity determination unit determine that the non-reference face image is similar to the reference face image, the non-reference Group registration means for registering a face image as a group of the reference face images (for example, a group management DB registration unit 340 in FIG. 21) may be further included.

An information processing method and program according to one aspect of the present invention include an imaging step (for example, step S2 in FIG. 14) for capturing an image of a predetermined range at an entrance of a game store, and an image captured by the processing of the imaging step. A feature amount extracting step (for example, step S23 in FIG. 14) for extracting a feature amount of the face image of the person to be collated, and a plurality of the person to be collated on the image captured by the processing of the image capturing step. Attribute estimation step (for example, step S24 or S5 in FIG. 14) for estimating an attribute code set by a table comprising any one of these attribute information or a combination thereof, and a pre-registered registrant face image storage step of storing in association with the attribute code (e.g., step S64 of FIG. 20) and, paired with the attribute code by the processing of the storage step Advance and registered registrant's face image are accumulated with the a collation object person of the face image, based on the feature quantities and attributes code estimated by the processing of the attribute estimation step of the face image matching The collation determination step (for example, step S28 in FIG. 14) for determining whether or not the collation target person is the registrant and the collation target person is the registrant by the processing of the collation determination step. If determined, a notification step (for example, step S43 in FIG. 14) for notifying that the verification target person is the registrant is included.

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

  The amusement stores 1-1 to 1-n are so-called pachinko stores or pachislot stores. These amusement stores 1-1 to 1-n are affiliated stores or member stores of the biometric information management center or third party amusement store management center, and stores that need to manage a plurality of stores in an integrated manner. It is. Each game store 1-1 to 1-n is 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 these buses and the Internet are used. Via each other, biological information and third-party amusement store management information are exchanged. In the following description, when it is not necessary to distinguish each of the game stores 1-1 to 1-n, the game store 1 will be simply referred to, and the other configurations will be similarly referred to.

  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 mainly managed 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 manages the biometric information management center, and is a registered player DB 252 (FIG. 12) managed by a biometric information management database (hereinafter also referred to as DB) 3. the updating based on unregistered player DB 251 (FIG. 12) generated by each amusement shop 1 together, the latest registered player DB252 the updated distributes the biometric information recognition device 21 of the gaming facility 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 is managed by the third-party amusement store management database (DB) 5. both the the DB consisting of information updated based on the information supplied from the amusement shop 1, the latest media lending management information updated for delivering to the medium lending management device 27 of the gaming facility 1.

  The security center 10 is a server managed by a public security organization or a security company, and attributes such as sex, age, and height among registered players managed by the biometric information DB 22 for a specific gaming store 1 Search for criminals and missing persons based on information.

  The biological information recognition apparatus 21 includes image processing units 39-1 to 39 based on images taken by the cameras 38-1 to 38-m, the in-store cameras 40-1 to 40-p, and the entrance cameras 42-1 to 42-q. -(m + p) and entrance image processing units 41-1 to 41-q extracted in advance and registered in advance in the biological information database 22 based on the facial image information supplied via the biological information bus 31 When the face image matches, the registered player is notified of the visit to the mobile terminal 20 or displayed on the display unit 23 such as a CRT (Cathode Ray Tube) or LCD (Liquid Crystal Display). When the face image registered in the biometric information database 22 is collated and does not match, the biometric information recognition device 21 accesses the biometric information management database 3 and registers it as an unregistered player in the unregistered player DB 251. .

  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 gaming store management device 24 determines whether or not the game balls 36 are played or the medals are paid out, the call information of the players of the gaming tables 36-1 to 36-m, or the monitoring status such as the occurrence of an error. The above process is executed, and the execution result is displayed on the display unit 25 such as a CRT or LCD. The game store management device 24 includes a settlement machine 33, a lending machine 34, a counter 35, a game machine 36-1 to 36-m, and a game machine peripheral terminal 37, a game machine peripheral terminal 37-1 to 37-m, respectively. The supplied information is managed by the gaming machine management database 26 in association with identification information (for example, gaming machine number) for identifying each of the supplied information.

Both media lending management device 27, settlement vending machine 33, lending machine 34, and based on information from the counting machine 35, when managed using medium lending management database 29 the medium lending management information of game media to be lent, medium When the medium lending management information registered in the lending management database 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 network 9, and the medium lending management is performed. Accumulate in 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, a prepaid card or the like when playing the game on the gaming table 36. At this time, lending machine 34, information such as the remaining number of the accepted money and prepaid card are both supplies information of the number of lending game media to media lending management device 27. Thus, the medium lending management device 27, information such as the remaining number of the accepted money and prepaid card are both registers information of the number of lending game media to media lending management database 29.

  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 machine 33 settles and pays out the cash based on the remaining number of game media lent as a frequency such as a prepaid card. At this time, the checkout vending machine 33 supplies the remaining amount of the prepaid card 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, a receipt, or the like.

  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 stand peripheral terminals 37-1 to 37-m are so-called stand machines provided corresponding to the respective game stands 36-1 to 36-m. The same as the lending machine 34). 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 gaming machine management device 24 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 functions for acquiring biometric information.

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

  Further, as shown in FIG. 4, for example, the cameras 38-1 to 38-m are provided with convex portions 71-1 to 71-4 on the game stand 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.

  Furthermore, for example, as shown in FIG. 6, the cameras 38-1 to 38-4 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, as the camera 36 is installed in the installation unit 81 of FIG. 6, as shown in FIG. 7, the player is imaged within the reading range φ.

  The entrance cameras 42-1 to 42-q and the in-store cameras 40-1 to 40-p are installed at entrances and predetermined places in the store of the amusement store 1, and the captured images are respectively input to the entrance image processing units 41-1 to 41-41. -q and the image processing units 39- (m + 1) to 39- (m + p).

  The entrance cameras 42-1 to 42-q and the in-store cameras 40-1 to 40-p are set as shown in FIG. 8, for example. FIG. 8 shows an installation example of the entrance cameras 42-1 to 42-q and the in-store cameras 40-1 to 40-p in the game store 1.

  That is, in FIG. 8, the entrances 112-1 to 112-3 are provided, and the entrance cameras 42-1 to 42-3 take images of the players who enter the store from each entrance 112. Further, the in-store cameras 40-1 to 40-10 are set at positions where each side 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, are disposed so as to sandwich the island facilities 111 in the vertical direction in the figure. Since the camera 38, the entrance camera 42, and the in-store camera 40 all have a pan / tilt / zoom function, as shown in FIG. 8, the in-store cameras 40-1 to 40-10 are arranged so that the game table All players who play at 36 can take images with any of the in-store cameras 40-1 to 40-10.

  Further, the in-store camera 40-a is provided in front of the lending machine 34, the in-store camera 40-b is provided in front of the checkout machine 33, and the in-store camera 40-c is provided in the counter 35. It is provided in front, and it is possible to take an image of a player who uses the lending machine 34, the checkout machine 33, and the counter 35, respectively.

  That is, as shown in FIG. 8, at the game store 1, the player who visits the store, the player who plays at the game stand 36, and the player who uses the lending machine 34, the checkout machine 33, and the counter 35 The camera 38, the entrance camera 42, and the in-store camera 40 are installed so that almost all of the actions that the player is supposed to take in the gaming store 1 can be monitored.

  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 in-store camera 40) 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 rectangular image to the transmission unit 203. The transmission unit 203 transmits the face image to the biometric information recognition device 21. The transmission unit 203 includes a memory 203a that stores a camera ID and an RTC (Real Time Clock) 203b that generates time information. The transmission unit 203 transmits a face image to the biological information recognition device 21. when the camera 38 has supplied the image (or store cameras 40) together with a camera ID identifying individually reads the current date from RTC203b, transmits subjected to the face image to the biological information recognition device 21. In the following description, it is assumed that the face image supplied from the image processing unit 39 includes information about the camera ID and the current date and time.

  Next, a configuration example of the entrance image processing unit 41 will be described with reference to FIG. Note that the image acquisition unit 211 and the transmission unit 213 in FIG. 10 have the same configuration as the image acquisition unit 201 and the transmission unit 203 in FIG. 9, and therefore description thereof will be omitted as appropriate.

  The face image extraction unit 212 extracts a rectangular image composed of a face image from the image supplied from the image acquisition unit 211 using a pattern such as the arrangement of the parts constituting the face, and supplies the extracted rectangular image to the transmission unit 213. At that time, the face image position detection unit 212a detects the position where the face image on the image is extracted when the size of the rectangular image composed of the extracted face images is a predetermined size, and the detection result is used as the height estimation unit. Supply to 212b. The height estimation unit 212b collates with a height table 214 in which height information set in association with a position where a face image of a predetermined size is extracted, and estimates the height of a person in the face image. When the rectangular image composed of the face images has a predetermined size, the face image extraction unit 212 adds the estimated height information and supplies the information to the transmission unit 213.

  Therefore, when transmitting the face image to the biometric information recognition device 21, the transmission unit 213 uses the camera ID that individually identifies the entrance camera 42 that has supplied the image, the current date and time read from the RTC 203b, and the estimated attribute information. The height information is attached to the face image and transmitted to the biological information recognition apparatus 21. In the following description, it is assumed that the face image supplied by the entrance image processing unit 41 includes the camera ID, current date information, and height information as estimated attribute information.

  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 the face image supplied from the entrance image processing unit 41 (or the image processing unit 39) and supplies it to the collation unit 222. The collation unit 222 collates the face image acquired by the face image acquisition unit 221 with the registered player's face image registered in advance in the biometric information DB 22, and if there is a face image that is a candidate with a high degree of similarity. The face images up to the third candidate are displayed on the display unit 23 as a matching result. Further, the collation unit 222 supplies the supplied face image to the unregistered player database registration unit 223 when there is no candidate face image with a high similarity.

  More specifically, the feature amount extraction unit 231 of the matching unit 222 extracts a feature amount for identifying a face image, and supplies the feature amount together with the face image to the attribute estimation unit 232 and the extraction unit 233. The attribute estimation unit 232 includes an age estimation unit 232a and a gender estimation unit 232b, controls each of them, estimates the age and gender as the attributes of the person of the face image based on the feature amount, and each estimation result The information of age and gender is supplied to the extraction unit 233.

The extracting unit 233 controls the attribute code adding unit 223a based on the attribute information classified by the height added to the face image in addition to the age and gender supplied from the attribute estimating unit 232 as attributes. Then, a corresponding attribute code is added, and a face image having the same attribute code is extracted from the biological information DB 22 and supplied to the similarity calculation unit 234. Similarity calculation unit 234, both when extracting the feature quantity of the registered player's face image registered narrowed by the attribute code extracted from the biometric information DB22 from extractor 233 is supplied from the feature value extracting unit 231 The facial image supplied from the facial image acquisition unit 221 is obtained by using the feature amount to obtain the similarity with the facial image narrowed down by the attribute code among the registered players registered in the biometric information DB 22. , And face images with the top three most similarities are supplied to the similarity determination unit 235. More specifically, the similarity calculation unit 234, for example, based on various facial feature amounts such as the ratio of 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 determination unit 235 includes a similarity between the similarity of the face image with the highest similarity and the face image with the highest similarity, supplied from the similarity calculation unit 234, and a predetermined threshold value. If the registered face image that is ranked first is similar to the face image supplied from the face image acquisition unit 221 based on the comparison result (the similarity is higher as the degree of similarity is higher). If the similarity is higher than a predetermined threshold, or if the similarity is lower, the similarity is lower than the predetermined threshold) and supplies the information of the image and the similarity on the display unit 23, when the display together, and supplies to the communication unit 224. In addition, the similarity determination unit 235 compares the similarity with the first-ranked face image and a predetermined threshold, and based on the comparison result, the first-registered face image is received from the face-image acquiring unit 221. When the supplied face image is not similar, the face image supplied from the face image acquisition unit 221 is supplied to the unregistered player database registration unit 223.

  The unregistered player database registration unit 223 registers the face image, which has been supplied as being unregistered by the verification unit 222, in the unregistered player DB 251 of the biometric information management database 3.

  The operation unit 225 includes buttons, a mouse, a keyboard, and the like. The operation unit 225 is operated when any of the face images displayed on the display unit 23 with the above-mentioned similarity ranked in the top three is selected, and the operation result Is supplied to the communication unit 224. The communication unit 224 includes a modem or the like, and distributes the selected face image to the mobile terminal 20 based on an operation signal from the operation unit 225.

  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 face image of the registered player corresponding to the similarity is. However, for example, when the similarity is expressed as a difference sum in the respective feature amounts between the captured face image and the face image registered as the registered player, the similarity determination unit 235 determines that the similarity is a threshold value. If it is smaller than that, the captured face image is regarded as a registered player's face image, or in the case of an average ratio or the like, it is greater than or equal to a predetermined value in the range of 0 to 1 and close to 1. If it is a value, it can be considered that they are the same person.

  When a new registered player DB 252 (FIG. 11) is distributed from the biometric information management center 2, the database management unit 226 updates the biometric information DB 22 based on the new registered player DB 252.

  The search unit 227 performs customer registration by collecting and grouping face images of the same person among registered player's face images stored in the biometric information DB 22. In addition, the search unit 227 searches and extracts the registered player information stored in the biometric information DB 22 based on the search conditions supplied when the operation unit 225 is operated, and displays the information on the display unit 23. To do. The detailed configuration of the search unit 227 will be described later with reference to FIG.

  Next, a configuration example of the biological information management center 2 will be described with reference to FIG.

  The biometric information management center 2 includes a DB distribution unit 241, a DB update unit 242 and a DB update determination unit 243. The registered player DB252 stored in the biometric information management DB3 is transferred to the unregistered player DB251. Update based on. More specifically, the DB update determination unit 243 has a built-in RTC (Real Time Clock) 243a that generates time information. When a predetermined time elapses based on the built-in RTC 243a, the biological information management DB3 is accessed to determine whether or not a new unregistered player has been registered in the unregistered player DB251.

  When a new unregistered person is registered in the unregistered player DB 251, the DB update determination unit 243 notifies the DB update unit 242 to that effect. The DB update unit 242 accesses the unregistered player DB 251 to determine whether or not there is an unregistered player that has been registered a predetermined number of times among registered unregistered players. When there is an unregistered player registered as an unregistered player, the registered player DB 252 is read, and an unregistered player registered for a predetermined number of times or more is registered in the registered player DB 252 and updated. Further, when the registered player DB 252 is updated, the DB update unit 242 notifies the DB distribution unit 241 of the update.

  When notified by the DB update unit 242 that the registered player DB 252 has been updated, the DB distribution unit 241 accesses the biometric information management DB 3 and reads the registered player DB 252 to recognize the biometric information of each gaming store 1. Delivered to the device 21.

  Next, a configuration example of the mobile terminal 20 will be described with reference to FIG.

  The communication unit 271 is configured by a modem or the like, and exchanges data with the biometric information recognition device 21 via a wireless communication network in the game store 1. In addition, the communication unit 271 displays information indicating that a player with a face image similar to the face image supplied from the image processing unit 39 and the entrance image processing unit 41 is delivered from the biological information recognition device 21. Acquired and supplied to the image processing unit 272.

The image processing unit 272 is based on information indicating that a player with a face image similar to the face image supplied from the image processing unit 39 and the entrance image processing unit 41 supplied from the communication unit 271 has visited the LCD. both when generating an image to be displayed on the display unit 273 constituted by such on the display unit 273.

  Next, the registered player visit monitoring process will be described with reference to the flowchart of FIG.

  In step S1, the entrance camera 42 determines whether or not the door of the entrance is opened based on the information of the image being captured or the signal from the door of the entrance and exit until the predetermined time elapses. Repeat the process.

  If it is determined in step S1 that the door is opened, in step S2, the entrance camera 42 captures an image of the installed range and supplies the captured image to the entrance image processing unit 41. The image acquisition unit 211 of the entrance image processing unit 41 acquires the supplied image and supplies it to the face image extraction unit 212.

  In step S3, the face image extraction unit 212 extracts a player's face image from the supplied image. More specifically, the face image extraction unit 212 extracts a face image from, for example, an arrangement of a characteristic part such as an eye or a nose, where the skin is exposed from the color of the captured image.

  In step S4, the face image position detection unit 212a detects the position in the image of the face image of a predetermined size among the extracted player face images, and obtains information on the position of the detected face image as a height. It supplies to the estimation part 212b.

  More specifically, the face image position detection unit 212a determines which of the regions Z1 to Z4 in the image the extracted face image belongs to, for example, as shown in FIG. Is supplied to the height estimation unit 212b. FIG. 15 shows an image captured by the entrance camera 42 in which the horizontal direction is X pixels and the vertical direction is Y pixels, and whether the barycentric position in the face image area belongs to any of the areas Z1 to Z4 Thus, the face image position detection unit 212a detects a region where the face image exists as position information of the face image.

  In step S5, the height estimation unit 212b collates the position information of the face image supplied from the face image position detection unit 212a with the height table 214, estimates the height as an attribute of the face image, and estimates the estimated height information. Is attached to the face image and supplied to the transmission unit 213.

  That is, height information corresponding to which of the areas Z1 to Z4 of the image in FIG. 15 belongs is recorded in the height table 214 as a table. The height estimation unit 212b refers to the height table 214 for the region of the detection position of the face image supplied from the face image position detection unit 212a, and determines the height of the person in the face image based on the corresponding height information. presume. For example, in FIG. 15, when a face image of a predetermined size belongs to the area Z1, the height is estimated as 140 to 160 cm, and when a face image of the predetermined size belongs to the area Z2, the height is estimated as 160 to 180 cm. In the height table 214, when the face image of a predetermined size belongs to the area Z3, the height is estimated as 180 to 200 cm, and when the face image of the predetermined size belongs to the area Z4, the height is estimated as 200 cm or more. It is recorded.

  The height table 214 is defined in this way because the vertical position of the face image existing at a predetermined distance from the entrance camera 42 in the image obtained by the entrance camera 42 capturing a predetermined direction is This is because the height depends on the height, and the height can be estimated based on the position of the face image in the vertical direction. However, among the face images in the image captured by the entrance camera 42, only the face image existing at a predetermined distance from the entrance camera 42 is used for estimating the height, but the distance to the face image itself is used. Since there is no way to measure, set the average size of the face image when capturing a face of average size at a predetermined distance as the predetermined size L1, and the face image of that size L1 of the predetermined distance By treating it as a face image, it is used for estimation of the face image.

  For example, as shown in the left part of FIG. 16, the face image of the person H1 that has passed through the entrance 112 is the position P1 at which the height is measured, and the entrance camera 42 is an image as shown in the right part of FIG. When a face image of L1 pixels in the vertical direction as a predetermined size belongs to the region Z3, the height estimation unit 212b has been supplied from the face image position detection unit 212a to the height table 214. The height of the person in the face image is estimated by collating the region Z3 and reading out the information estimated that the corresponding height information is 180 to 200 cm.

  Further, for example, as shown in the left part of FIG. 17, the face image of the person H2 that has passed through the entrance 112 is the position P1 at which the height is measured, and the entrance as an image as shown in the right part of FIG. When captured by the camera 42, when a face image of L1 pixels in the vertical direction as a predetermined size belongs to the region Z2, the height estimation unit 212b is supplied from the face image position detection unit 212a to the height table 214 The height of the person in the face image is estimated by collating the area Z2 and reading out information that the corresponding height information is estimated as 160 to 180 cm.

  In FIG. 17, the face image of the person H1 is also captured. However, since the vertical size of the face image is L1 ′ (> L1) pixels that are not a predetermined size, the height should be measured. It is considered not to exist in P1, and the height is not estimated.

  As for the predetermined size L1 of the face image, as shown in FIG. 18, it depends on the relationship between the imaging distance of the entrance camera 42 and the face angle (the elevation angle where the angle at which the face is oriented in the horizontal direction is 0 degree). It is determined. FIG. 18 shows the relationship between the predetermined size of the face image with respect to the image of 640 × 480 pixels in the horizontal direction × vertical direction, the imaging distance, and the face angle, and the diamond point is the predetermined size of the face image. Yes, square points indicate the face angle. As shown in FIG. 18, if the imaging distance is short, the predetermined size of the face image is large, so that the recognition accuracy of the face image is expected to be high. However, if the face angle is not large, the recognition accuracy decreases. On the other hand, if the distance is long, the predetermined size of the face image becomes small, but the recognition accuracy of the face image of a normal person with a small face angle improves. For this reason, it is necessary to set the imaging range of the entrance camera 42 in accordance with a balance with a predetermined size of a usable face image. Under this condition, it can be said that the imaging distance is preferably about 5 to 10 m, for example.

In step S 6, the transmission unit 213 transmits the face image supplied from the face image extraction unit 212 to the biological information recognition device 21. In this case, transmission unit 213, a camera 38, both when the camera ID identifying each store camera 40 or entrance camera 42, read from the memory 213a, adds date and time information to send the face image read from RTC213b, in the face image And transmitted to the biometric information recognition device 21.

  In step S21, the face image acquisition unit 221 of the biological information recognition apparatus 21 acquires a face image. In step S22, the face image acquisition unit 221 extracts one of the unprocessed face images from the supplied face images and supplies the extracted unprocessed one to the feature amount extraction unit 231.

In step S23, the feature extraction unit 231 of the verification unit 222 extracts the feature value from a face image supplied, supplies both the attribute estimating unit 232 and the extraction unit 233 and the face image.

  In step S24, the attribute estimation unit 232 controls the age estimation unit 232a and the sex estimation unit 232b, respectively, and based on the supplied facial image feature quantity, the age (age group) and sex of the person in the face image And the estimation result is supplied to the extraction unit 233. More specifically, the age estimation unit 232a estimates the age based on the wrinkles generated by various aging, the presence or absence of spots, and the like based on the feature amount of the face image. In addition, the gender estimation unit 232b estimates gender based on the feature amount of the face image based on the presence or absence of wrinkles or the presence or absence of a throat buddha.

  In step S25, the extraction unit 233 controls the attribute code adding unit 223a to set the attribute code based on the attribute information set based on the attribute information including gender, age, and height. That is, the attribute code is set in a table as shown in FIG. 19, for example, and is a code set based on the attribute information such as sex, age, and height.

  In FIG. 19, the upper and lower tiers are divided according to gender, and each of the upper and lower tiers is divided into seven stages according to height (136 cm to 146 cm, 146 cm to 156 cm, 156 cm to 166 cm, 166 cm to 176 cm, 176 cm or more Less than 186cm, more than 186cm and less than 196cm, more than 196cm). In addition, the horizontal direction is divided into four stages according to the age (under 20 years old, 20 to 40 years old, 40 to 60 years old, 60 years old and over). Therefore, the attribute code is composed of 56 codes from A to BD. For example, as attribute information, the age is 20 to 40 years old, the gender is female, and the height is 156 to 166 cm The attribute code is set to “AL”, and as attribute information, the age is between 40 and 60 years old, the gender is male, and the height is 176 cm. If it is estimated that the distance is less than 186 cm, the attribute code is set to “S”.

  In step S26, the extraction unit 233 extracts the face image of the registrant to which the same attribute code is calculated from the biometric information DB 22 using the attribute code, and supplies the extracted facial image to the similarity calculation unit 234. That is, the face image registered in the biometric information DB 22 is supplied from the attribute estimation unit 232 because the attribute code is set based on the attribute information including the sex, the age, and the height as described above. In addition to the age and gender attribute information, a face image having the same attribute code set as the attribute code set by the height information as the attribute information attached to the face image is extracted.

  Since only the information of the corresponding face image is extracted from the biological information DB 22 based on the attribute code in this way, it is possible to suppress the calculation amount of the similarity that affects the processing time, and thus the biological information DB 22 This makes it possible to improve the search speed of the registered player's face image registered in.

In step S27, the similarity calculation unit 234 calculates the distance between the eyes, the distance from the chin to the forehead, and the length from the chin to the nose for the face image extracted from the extraction unit 233 based on the attribute code. Obtain various facial feature quantities such as ratios, calculate the difference sum, average ratio, or ratio sum of each as the similarity, calculate the ranking of the similarity as the calculation result, and face images up to the top three supplies information of the similarity, both the similarity determination unit 235 and the face image supplied from the feature value extracting unit 231 and.

  In step S28, the similarity determination unit 235 determines whether the highest similarity is greater than a predetermined threshold based on the top three face images and similarity information supplied from the similarity calculation unit 234. Determine whether or not. That is, the similarity determination unit 235 is a registered player who is most similar (a registered game that is most similar to the facial image acquired by the facial image acquisition unit 221 among facial images registered in the biometric information DB 22). In this case, the similarity of the registered player having the highest similarity is compared with a predetermined threshold.

  Note that, as described above, the similarity between the face image of the registered player who is most similar to the captured face image is not necessarily the highest because of the definition of the similarity. And the threshold value may differ from those in this example.

  In step S29, the similarity determination unit 235 controls the display unit 23 with a notification screen indicating that the top three face images supplied from the similarity calculation unit 234 are candidates for the registered player's face image. To display.

  In step S30, the communication unit 224 determines whether any of the candidate face images has been selected by operating the operation unit 225, that is, for example, if a notification screen is displayed on the display unit 23, The unit 225 determines whether an operation for selecting any of the candidate face images has been performed.

  In step S30, for example, when a face image that is the first candidate is selected, in step S31, the communication unit 224 selects the face image that is the first candidate and the camera image captured by the entrance camera 42. Is transmitted to the mobile terminal 20 to notify that the corresponding registered player has visited the store.

In step S41, the communication unit 271 determines whether or not the registered player has been notified of the store visit, and repeats the processing until the notification is received. For example, in step S41, for example, when the registered player's visit is notified by the process of step S31, the communication unit 271 sends the registered player's visit transmitted from the biometric information recognition device 21 in step S42. Upon receiving the notification together supplies camera image captured by the face image and the entrance camera 42 registered player sent in conjunction with the notification to the image processing unit 272. The image processing unit 272 processes the information of the selected face image and the camera image captured by the entrance camera 42 into information in a format that can be displayed on the display unit 273, and displays the information on the display unit 273 in step S43. .

  With the above processing, the staff in the game store 1 can recognize the visit of the registered player if the portable terminal 20 is possessed.

  In step S32, the face image acquisition unit 221 determines whether or not all the face images extracted by the extraction unit 233 have been processed. If there is an unprocessed face image, the process proceeds to step S22. Return. That is, the processes in steps S22 to S33 are repeated until the process is performed on all face images extracted by the extraction unit 233. If it is determined that the process has been completed for all face images, the process returns to step S21.

  On the other hand, if no candidate face image is selected in step S30, or based on the top three face images and similarity information supplied from the similarity calculation unit 234 in step S28, If the highest similarity is not greater than the predetermined threshold, that is, if the similarity is less than the predetermined threshold even in the face image of the most similar registered player, the similarity is determined in step S33. The determination unit 235 supplies the face image supplied from the entrance image processing unit 41 to the unregistered player database registration unit 223 together with the attribute code. The unregistered player database registration unit 223 accesses the biometric information management database 3 through the biometric management information bus 6 and the public communication line network 8 to register the supplied face image in the unregistered player DB 251.

  If the face image supplied from the entrance image processing unit 41 by the biometric information recognition device 21 is not registered in the biometric information DB 22 by the above processing, the biometric information managed by the biometric information management center 2 The face image of the unregistered player is registered in the unregistered player DB 251 in the management DB 3.

  Next, the update process of the registered player DB 252 will be described with reference to the flowchart of FIG.

  In step S61, the DB update determination unit 243 of the biometric information management center 2 makes an inquiry to the RTC 243a, determines whether a predetermined time has elapsed, and repeats the process until the predetermined time has elapsed. For example, if it is determined in step S61 that the predetermined time has elapsed, in step S62, the DB update determination unit 243 accesses the unregistered player DB 251 of the biological information management DB 3, and an unregistered player newly It is determined whether or not it is registered, and the processes of steps S61 and S62 are repeated until it is determined that a new unregistered player is registered.

  In step S62, for example, if an unregistered player is newly registered by the process of step S32, the DB update determination unit 243 determines that the unregistered game newly registered in the unregistered player DB 251 in step S63. It is determined whether or not one of the users has been registered a predetermined number of times or more. If not, the process returns to step S61.

On the other hand, in step S63, for example, when it is determined that there is an unregistered player registered in the unregistered player DB 251 a predetermined number of times or more, the DB update determination unit 243 determines in step S64 that the DB update unit 242 The registered player DB 252 is notified that it should be updated. In response to this, DB updating unit 242 accesses the unregistered player DB 251, both when read all the information of unregistered player's face image registered predetermined number of times or more, to access the registered player DB 252, An ID for identifying the face image is attached to the information of the face image of the unregistered player who has been registered a predetermined number of times or more, and is additionally registered in the registered player DB 252 and updated. Further, the DB update unit 242 notifies the DB distribution unit 241 that the registered player DB 252 has been updated. Note that, when the update of the registered player DB 252 is completed, unregistered players that have been registered a predetermined number of times or more are deleted from the unregistered player DB 251.

In step S65, DB distribution unit 241 accesses the registered player DB252 newly updated biological information management DB3, when read together, the registered player DB252 read the database management unit 226 of the biological information recognizer 21 To deliver.

  In step S81, the database management unit 226 determines whether or not a new registered player DB 252 updated from the biometric information management center 2 has been distributed, and repeats the processing until it is distributed.

In step S81, for example, when the newly updated registered player DB 252 is distributed from the DB distribution unit 241 of the biological information management center 2 by the process of step S65, the database management unit 226 distributes in step S82. both acquires the registered player DB 252 coming is, based on the information of the registered player DB 252, and updates the biometric information DB 22. More specifically, the database management unit 226 copies and overwrites the newly distributed information of the registered player DB 252 in the biometric information DB 22.

  As a result of the above processing, when registered in the unregistered player DB 251 as an unregistered player at a predetermined number of times in any of the game stores 1-1 to 1-n, by additionally registering in the registered player DB 252, Since it will be registered as a database in the biological information DB 22 of any biological information recognition device 21 of any of the gaming stores 1-1 to 1-n, when captured by the entrance camera 42 in a plurality of gaming stores 1, The visit to the store will be notified as a registered player. In addition, since the registered player DB 252 is updated based on information from each of the game stores 1-1 to 1-n, it becomes possible to generate customer store records at a plurality of stores and to integrate customer store records. Management is possible.

In the above, as shown in the process of step S1 in the flowchart of FIG. 14, the face image in the image captured at the opening timing of the doorway and the face of the biometric information DB22, which is the same database as the registered player DB252 both the image to determine whether the visit are collated, if not a registered player is registered in the unregistered player DB251 as an unregistered player, and registered as a predetermined number of times unregistered player, registration Although the example registered in the player DB 252 has been described, the timing at which an image is captured is not limited to this. For example, it is detected that a banknote is jammed in the gaming machine peripheral terminal 37, or the gaming machine 36 In this case, the camera 38 or the in-store camera 41 may be used to capture an image when an abnormal operation such as a ball jam or a medal jam is detected. In this way, by registering a specific player at the time of an abnormal operation, for example, when an illegal act is performed using the abnormal operation, it is possible to detect this.

  Further, in the above, as shown in the process of step S1 in the flowchart of FIG. 14, the example of extracting the face image at the timing when the door is opened has been described, but the imaging is not performed without deciding the timing of imaging specially. If a face image is extracted while continuing, it may be collated.

  According to the above, it is possible to realize not only customer visit information at each store but also collection of customer visit records at a plurality of stores and integrated management.

  By the way, with the above processing, the face images that come to the amusement store are accumulated sequentially, but the accumulated face images will continue to increase and become difficult to manage. Is expected. In addition, in the case of regular customers, since the same player's face images are recorded in large numbers, the same person's face images are collected in the same file by processing such as grouping for each customer. It is expected that it will be required to be able to improve administrative efficiency in the same way.

Therefore, the search unit 227 searches for a face image stored in the biological information DB 22 according to a condition requested by operating the operation unit 225, and the same among the searched face images. both the customer registration by grouping face images appear to a person's face image as the same customer face images, by displaying on the display unit 23, when improving the efficiency administrative facial image together, individually It is possible to analyze store visit information of customers.

  FIG. 21 is a block diagram showing a detailed configuration example of the search unit 227 and the security center 10. As shown in FIG.

  The face image acquisition unit 331 extracts a face image from the biometric information DB 22 based on the search condition supplied from the condition reception unit 342 and stores the face image in the buffer 332. At this time, the face image acquisition unit 331 also stores the ID, camera ID, and date / time information in the biometric information DB 22 in the buffer 332 together.

  The feature amount extraction unit 333 is basically the same as the feature amount extraction unit 231 in the collation unit 222, extracts the feature amount of the face image from the face image stored in the buffer 332, and sequentially determines the age estimation unit 334. To the sex estimation unit 335 and the extraction unit 336. The age estimating unit 334 and the gender estimating unit 335 have the same functions as the age estimating unit 232a and the gender estimating unit 232b described above, and supply the estimated attribute information to the extracting unit 336.

  The extraction unit 336 temporarily stores the feature amount and attribute information of the reference face image in the feature amount buffer 337 and compares the attribute information of the non-reference face image with the attribute information stored in the feature amount buffer 337. The feature amount of the matched face image is supplied to the similarity calculation unit 338.

  The similarity calculation unit 338 is basically the same as the similarity calculation unit 234, and is stored in the feature amount buffer 337 and the feature amount of the non-reference face image sequentially supplied from the feature amount extraction unit 333. The similarity is calculated using the feature amount of the reference face image, and the ID of each of the non-reference face image and the reference face image obtained as the calculation result is supplied to the similarity determination unit 339. To do.

  The similarity determination unit 339 compares the similarity between the non-reference face image and the reference face image with a predetermined threshold, and determines that the non-reference face image and the reference face image are similar. The face image and the reference face image are supplied to the group management DB registration unit 340.

  The group management DB registration unit 340 sets a new customer ID corresponding to the reference face image, and associates the ID of the non-reference face image supplied from the similarity determination unit 339 with the customer ID. Register customers in DB341.

The display image generation unit 343 controls the extraction unit 343a based on the condition supplied from the condition reception unit 342 to search the group management DB 341, and sets the ID on the biological information DB 22 corresponding to the searched customer ID. the corresponding face image, both when the extracted from the buffer 332, generates display image on the display unit 23. Further, when there is an instruction to search for a specific customer ID, the display image generation unit 343 controls the confirmation unit 343b to check whether or not the customer ID exists. Only perform the process.

  In response to a request from the security center 10, the survey processing unit 344 searches for a player to be surveyed based on attributes such as age, gender, and height, and transmits the search result to the security center 10.

  The communication unit 344a includes a modem and exchanges information with the security center 10. The attribute code generation unit 344b generates an attribute code for identifying a player to be searched from the age, sex, and height of a person who has requested a survey from the security center 10. The attribute code is generated, for example, under the conditions described with reference to FIG. The survey player search unit 344c searches for a player registered in the biometric information DB 22 based on the attribute code generated by the attribute code generation unit 344b. The information of the player who has been sent is transmitted to the security center 10.

  The operation unit 10a of the security center 10 is composed of, for example, a keyboard, a button, and the like. The operation unit 10a is operated when a specific player is requested to be inspected for each game store 1, and the age of the player to be investigated is Operated when inputting information such as gender and height. The communication unit 10b is, for example, a modem, and is used when a survey request is transmitted to the game store 1 or when a survey result for the survey request is received. The display unit 10c includes a CRT, an LCD, and the like, and displays the operation content of the operation unit 10a, the investigation result received by the communication unit 10b, and the like.

  Next, customer registration processing by the search unit 227 of FIG. 21 will be described with reference to the flowchart of FIG.

  In step S101, the condition receiving unit 342 determines whether or not the customer registration process is instructed by operating the operation unit 225, and repeats the process until instructed. In step S101, for example, when a customer registration process is instructed, in step S102, the condition reception unit 342 notifies the display image generation unit 343 that the customer registration process is instructed. In response to this notification, the display image generation unit 343 causes the display unit 23 to display a face image search distribution screen that prompts input of search conditions.

  In step S103, the condition receiving unit 342 determines whether or not the search unit is input by operating the operation unit 225, and the process is repeated until it is determined that the input is performed. For example, when a search condition is input in step S103, the process proceeds to step S104.

  In step S104, the condition receiving unit 342 supplies the search condition information input by operating the operation unit 225 to the face image acquiring unit 331. The face image acquisition unit 331 extracts an unprocessed face image from the biometric information DB 22. In step S105, the face image acquisition unit 331 determines whether or not the extracted face image matches the search condition supplied from the condition reception unit 342. In step S105, for example, when the extracted face image matches the search condition, the face image acquisition unit 331 stores the extracted face image in the buffer 332 in step S106. If the extracted face image does not match the search condition in step S105, the process in step S106 is skipped.

  In step S107, the face image acquisition unit 331 determines whether or not an unprocessed face image exists in the biometric information DB 22. If it is determined that there is an unprocessed face image, the process returns to step S104. . In other words, the processing of steps S104 to S107 is repeated until there are no unprocessed face images, and only the face images that match the search condition are stored in the buffer 332.

  If it is determined in step S107 that there is no unprocessed face image, the process proceeds to step S108.

  In step S108, a grouping process for setting and grouping customer IDs for the same face image among the face images stored in the buffer 332 is executed.

  Here, the grouping process will be described with reference to the flowchart of FIG.

  In step S121, the feature amount extraction unit 333 extracts an unprocessed reference face image from the face image information stored in the buffer 332. That is, the feature amount extraction unit 333 extracts a reference face image from the face images stored in the buffer 332 for grouping.

  In step S122, the feature amount extraction unit 333 extracts the feature amount of the reference face image and supplies the feature amount to the age estimation unit 334, the gender estimation unit 335, and the extraction unit 336.

  In step S123, the age estimation unit 334 and the gender estimation unit 335 estimate the age and gender based on the feature amount of the reference face image, respectively, and supply them to the extraction unit 336. In addition to the estimated age and gender attribute information of the reference face image, the extraction unit 336 stores the height attribute information included in the face image in the feature amount buffer 337 together with the feature amount.

  In step S124, the feature amount extraction unit 333 extracts an unprocessed non-reference face image from the buffer 332, and in step S125, extracts a feature amount of the non-reference face image to obtain an age estimation unit 334, a gender estimation unit 335, And supplied to the extraction unit 336. At this time, ID information in the biological information DB 22 attached to the reference face image and the non-reference face image is also supplied to the extraction unit 336.

  In step S126, the age estimation unit 334 and the sex estimation unit 335 estimate the age and sex based on the feature amounts of the reference face image, respectively, and supply the estimation unit 336 with the age and sex. In addition to the estimated age and gender attribute information of the non-reference face image, the extraction unit 336 generates height attribute information included in the face image.

  In step S127, the extraction unit 336 accesses the feature amount memory 337, reads the attribute information of the reference face image, compares it with the attribute information of the non-reference face image, and determines whether or not they match.

If it is determined in step S127 that the attribute information of the reference face image matches the attribute information of the non-reference face image, in S128, the extraction unit 336 sends the feature amount of the non-reference face image to the similarity calculation unit 338. Supply information. In response to this, the similarity calculation unit 338 uses the feature amount of the non-reference face image supplied from the extraction unit 336 and the feature amount of the reference face image stored in the feature amount buffer 337, to thereby generate a reference face. It calculates a similarity between the image and the non-reference face image, and supplies both the similarity determination unit 339 and the ID in the biological information DB22 reference face images and non-reference face image.

  In step S129, the similarity determination unit 339 determines whether or not the reference face image and the non-reference face image are similar, that is, whether or not the similarity is greater than a predetermined threshold (the more similar the similar, If the degree is high, it is determined whether or not the degree of similarity is greater than a predetermined threshold.

  In step S129, for example, when it is determined that the similarity is greater than a predetermined threshold and both are similar, in step S130, the similarity determination unit 339 determines the biometric information of the reference face image and the non-reference face image. The ID in the DB 22 is supplied to the group management DB registration unit 340. The group management DB registration unit 340 registers the IDs of the supplied reference face image and non-reference face image in the biological information DB 22 in the group management DB 341.

  More specifically, for example, as shown in FIG. 24, the group management DB 341 is assigned the ID in the biometric information DB22 of the reference face image for each customer ID, and the biometric information DB22 of the non-reference face image having a high degree of similarity. ID (biological information DB-ID) is accumulated. Therefore, in step S130, the group management DB registration unit 340 searches for the customer ID in the group management DB 341 based on the ID in the biological information DB 22 of the reference face image supplied as a result of determining that the similarity is high. . At this time, if the search cannot be performed, the group management DB registration unit 340 sets a new customer ID and registers the ID in the biometric information DB 22 of the corresponding reference face image. Furthermore, the group management DB 341 registers the ID in the biological information DB 22 of the non-reference face image as the biological information DB-ID corresponding to the searched customer ID or the newly set customer ID.

  In FIG. 24, the customer ID, the reference face image ID, and the biometric information DB-ID are recorded from the left, and the customer ID is set as 001, 002, 003... From the top, and the corresponding reference face image. Are registered as IDs 00001, 00003, and 00008 in the biometric information DB22. Further, as the ID in the biological information DB 22 of the non-reference face image that is recognized as having a high degree of similarity to the reference face image set for each customer ID, 00002,00015,... Corresponding to the customer ID = customer 001. .., 00004,00021,... Corresponding to the customer ID = customer 002 and 00001,040,... Corresponding to the customer ID = customer 003 are registered, and the customer ID = customer 001. The face image with ID = 00001 of the registered reference face image has a face image of 00002,00015,... As the ID of the biometric information DB22, and the ID of the reference face image registered with customer ID = customer 002 = 00003. The face image of 00004,00021,... As the ID of the biometric information DB22 in the face image of the user ID = the ID of the reference face image registered in the customer 003 = 00008 To 00010,00040, ... of the face image is shown to have been registered respectively.

  In step S131, the feature amount extraction unit 333 determines whether there is an unprocessed non-reference face image among the face images stored in the buffer 332, and there is an unprocessed non-reference face image. If yes, the process returns to step S124. That is, the processes in steps S124 to S131 are repeated until it is determined that all face images have been processed as non-reference face images.

  If it is determined in step S127 that the attribute information does not match or the similarity is not greater than a predetermined threshold value in step S129, that is, it is determined that they are not similar, the process proceeds to step S131.

  That is, if it is determined in step S127 that the attribute information does not match, it is determined that the attributes are not similar before the similarity is calculated, so the calculation of the similarity with a large processing load is omitted. As a result, it is possible to improve the processing efficiency and also improve the accuracy of similarity determination.

  If it is determined in step S131 that there is no unprocessed non-reference face image, in step S132, the feature amount extraction unit 333 is a face image that is not set as a reference face image among the face images stored in the buffer 332. If there is a face image that is not a reference face image, the process returns to step S121. That is, the processes in steps S121 to S132 are repeated until all of the face images registered in the buffer 332 are set as reference face images. If it is determined in step S132 that all face images have been set as reference face images, the process ends.

  That is, by the above processing, among the face images stored in the biometric information DB22, IDs in the biometric information DB22 of similar face images for each face image that matches the search condition are grouped and registered in the group management DB341. Is done.

  However, in the above processing, similar face image IDs are grouped and registered for all face images that match the search condition, so that groups composed of the same ID overlap. It is expected to be registered. Since the purpose in the above processing is to distribute the face images into several groups, it is not desirable that the same group occurs.

  Therefore, in the grouping process, it is determined that the face image is similar to any one of the face images, and a face image belonging to any one of the face image groups is not extracted as a reference face image or a non-reference face image. It may be.

  FIG. 25 is a grouping that is determined to be similar to any one of the face images, and that the face images belonging to any one of the face image groups are not extracted as the reference face image or the non-reference face image. It is a flowchart explaining a process. Note that the processing of steps S141, S143 to S145, and S147 to S154 in the flowchart of FIG. 25 is the same as the processing of steps S121 to S132 in the flowchart of FIG.

  That is, in steps S142 and S146, the feature amount extraction unit 333 reads the information of the group management DB 341, and the ID of the reference face image extracted in step S141 or the ID of the non-reference face image extracted in step S145 However, it is determined whether or not it is registered as a group of face images similar to any one of the face images set with the customer ID. If it is determined in steps S142 and S146 that the user is registered in any group, the process returns to steps S141 and S146, respectively.

  As a result of the above processing, it is determined that the extracted reference face image or non-reference face image is similar to any one of the face images, and corresponds to the face image assigned with any customer ID. The face image corresponding to the ID registered in the group management DB 341 is not the target of the face image to be distributed, so basically the same face image is not redundantly registered in each group distributed by the customer ID. In other words, it becomes possible to suppress the generation of overlapping groups, and it is possible to efficiently realize the distribution of face images without waste. However, in the case of the grouping process in the flowchart of FIG. 25, the IDs of the face images to be grouped are expected to change depending on the order in which the unprocessed reference face images extracted from the biometric information DB 22 are extracted. The information registered in the group management DB 341 is expected to change depending on the order in which the reference face images are extracted.

  Therefore, the grouping process may be realized by switching the process corresponding to the flowchart of FIG. 23 and the process corresponding to the flowchart of FIG. 25 according to the operation mode.

  Now, the description returns to the flowchart of FIG.

In step S109, the display image generation unit 343 generates a display screen that displays information of the group management DB 341 registered by the grouping process in step S108, and displays the display screen on the display unit 23. That is, the display image generating unit 343 controls the extraction unit 343a, both when extracting a face image stored in the buffer 332, for example, be displayed as search results all the face images retrieved by the retrieval condition. Further, the display image generation unit 343 accesses the group management DB 341 and collectively displays the extracted face images for each ID in the biological information DB 22 grouped in association with the customer ID.

  In the above processing, if the attribute code registered together with the face image in the biometric information DB 22 is used, the above-described processing in steps S123 and S126 or steps S144 and S148 becomes unnecessary. In the processes of S127 and S149, both need only compare the attribute codes. Similarly, the age estimation unit 334 and the gender estimation unit 335 can be omitted from the search unit 227. However, by providing the search unit 227 with the age estimation unit 334 and the sex estimation unit 335, it is possible to set an attribute code different from the store visit monitoring process in the grouping process.

  Next, the inquiry screen display process will be described with reference to the flowchart of FIG.

  In step S171, the condition receiving unit 342 determines whether or not the operation unit 225 has instructed display of the inquiry screen, and repeats the process until the display of the inquiry screen is instructed. For example, if it is determined in step S171 that display of the inquiry screen has been instructed, in step S172, the condition receiving unit 342 notifies the display image generation unit 343 that display of the inquiry screen has been instructed. In response to this notification, the display image generation unit 343 causes the display unit 23 to display a display selection screen for selecting an inquiry display format.

  In step S173, the condition receiving unit 342 determines whether the operation unit 225 is operated and the person inquiry screen is selected. For example, when the operation unit 225 is operated and a display of a person inquiry screen is instructed, the process proceeds to step S174.

  In step S174, the condition receiving unit 342 supplies the display image generating unit 343 with an instruction to display the person inquiry screen. The display image generation unit 343 displays a screen requesting input of a customer ID that specifies a person to be referred to.

  In step S175, the display image generation unit 343 determines whether or not the operation unit 225 is operated via the condition reception unit 342 to input a customer ID for specifying a person to be inquired, and the customer ID is input. Repeat the process until In step S175, when the operation unit 225 is operated and a customer ID is input, the condition reception unit 342 supplies the input customer ID information to the display image generation unit 343.

  In step S176, the display image generation unit 343 controls the confirmation unit 343b to determine whether or not the supplied customer ID actually exists. More specifically, the display image generation unit 343 controls the confirmation unit 343b to access the group management DB 341 and confirm whether the customer ID supplied from the condition reception unit 342 exists.

In step S176, for example, when there is a customer ID that identifies a person to be displayed as a person inquiry screen, in step S178, the display image generation unit 343 accesses the group management DB 341 and is grouped by the customer ID. both reading the ID of the face image in the biological information DB 22, and controls the extraction unit 343a, causes the face image corresponding to the read ID is extracted from the buffer 332. Further, the display image generation unit 343 generates a person inquiry screen that displays the extracted face image for each date and causes the display unit 23 to display the screen.

  On the other hand, if the input customer ID does not actually exist in step S176, the process returns to step S174, and again requests input of the customer ID for specifying the person to be referred.

  If the display of the person inquiry screen is not instructed in step S173, the display of the store visit information inquiry screen is instructed, and the process proceeds to step S179.

  In step S179, the display image generation unit 343 accesses the group management DB 341, reads the face image IDs in the biological information DB 22 corresponding to all customer IDs, controls the extraction unit 343a, and stores the face images from the buffer 332. Let it be extracted.

  In step S180, the display image generation unit 343 generates a store visit information inquiry screen including store visit information for each date in association with the customer ID based on the information in the group management DB 341, and causes the display unit 23 to display it. .

With the above processing, it is possible to display store visit information in units of date for each customer ID or for all customer IDs for the face image searched under the search conditions described above. As a result, both becomes possible to efficiently manage the huge face image, it is possible to easily analyze the visit information for individual player.

  Next, the registered player DB investigation process by the search unit 227 and the security center 10 will be described with reference to the flowchart of FIG.

  In step S201, the security center 10 controls the operation unit 10a to determine whether or not the attribute information of the player to be surveyed including gender, age, and height has been input, and is determined to have been input. Until the same process is repeated. For example, when the attribute information of the player to be investigated is input, in step S202, the security center 10 determines whether the operation unit 10a is operated and the store ID for specifying the search store is input. If it is not determined that the input has been made, the process returns to step S201.

  In step S202, for example, when a store ID that specifies a search store is input, in step S203, the security center 10 controls the communication unit 10b to investigate the game store 1 corresponding to the store ID. Distribute the player's attribute information.

  In step S211, the investigation processing unit 344 controls the communication unit 344a to determine whether or not the attribute information of the player to be investigated has been distributed from the security center 10, and the same until the distribution is performed. Repeat the process.

  In step S211, for example, when attribute information has been distributed by the process of step S203, in step S212, the investigation processing unit 344 controls the communication unit 344a to receive the distributed attribute information and The code generation unit 344b is supplied to generate an attribute code based on the attribute information.

  In step S213, the survey processing unit 344 controls the survey player search unit 344c to search the biometric information DB 22 for the survey player based on the generated attribute code.

  In step S214, the survey processing unit 344 controls the survey player search unit 344c to determine whether there is a survey player corresponding to the attribute code, and if it exists, that is, it corresponds to the attribute code. If the survey player is registered in the biometric information DB 22, in step S215, the survey player search unit 344c is controlled to read the information registered in the biometric information DB 22, and the communication unit 344a is controlled. And sent to the security center 10 as the survey result.

  On the other hand, if there is no survey player corresponding to the attribute code in step S214, that is, if the survey player corresponding to the attribute code is not registered in the biometric information DB 22, the corresponding person is controlled by controlling the communication unit 344a. Is transmitted to the security center 10 as an investigation result.

  In step S204, the security center 10 controls the communication unit 10b, receives the survey result for the survey request from the game store 1, and displays the display result on the display unit 10c. That is, if it is a survey result based on step S215, information of the survey player that has been sent is displayed, if it is a survey result based on step S216, that is, if the corresponding person does not exist, A message to that effect is displayed.

  Through the above processing, it becomes possible to quickly investigate the players registered in the biological information DB 22 of a specific gaming store 1 based on the attribute information. Also, in the above, an attribute code is generated based on the attribute information and a search is performed based on the attribute code, so that it is possible to search for a survey player efficiently. Further, as a matter of course, the attribute information may be directly used as a search condition when searching for the survey player.

  Incidentally, the series of monitoring processing, customer registration processing, and inquiry screen display processing 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. 28 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) 1002 and a RAM (Random Access Memory) 1003 are connected to the bus 1004.

  The 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 the 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 1003. 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.

It is a figure which shows the structure of one Embodiment of the monitoring system to which this invention is applied. FIG. 2 is a diagram illustrating an installation example of the camera of FIG. FIG. 2 is a diagram illustrating an installation example of the camera of FIG. FIG. 2 is a diagram illustrating an installation example of the camera of FIG. FIG. 2 is a diagram illustrating an installation example of the camera of FIG. FIG. 2 is a diagram illustrating an installation example of the camera of FIG. FIG. 2 is a diagram illustrating an installation example of the camera of FIG. FIG. 2 is a diagram showing an installation example of the entrance camera and the in-store camera of FIG. FIG. 2 is a diagram illustrating a configuration example of an image processing unit in FIG. FIG. 2 is a diagram illustrating a configuration example of an entrance image processing unit in FIG. FIG. 2 is a diagram illustrating a configuration example of the biological information recognition device in FIG. FIG. 2 is a diagram for explaining a configuration example of a biological information management center and a biological information management DB in FIG. FIG. 2 is a diagram illustrating a configuration example of a mobile terminal in FIG. It is a flowchart explaining a registered player visit monitoring process. It is a figure explaining the process which estimates height. It is a figure explaining the process which estimates height. It is a figure explaining the process which estimates height. It is a figure explaining the process which estimates height. It is a figure explaining an attribute code. It is a flowchart explaining a registration player DB update process. It is a figure explaining the detailed structural example of a search part and a security center. It is a flowchart explaining a customer registration process. It is a flowchart explaining a grouping process. It is a figure explaining group management DB. It is a flowchart explaining the other grouping process. It is a flowchart explaining an inquiry screen display process. It is a flowchart explaining a registration player DB investigation process. It is a figure explaining a medium.

Explanation of symbols

1,1-1 to 1-n amusement store
2 Biometric Information Management Center
3 Biological information management database
4 Third-party amusement center management center
5 Third-party amusement store management database
6 Biological information management bus
7 Third-party amusement store management bus
8,9 Public communication network
10 Security Center
21 Biological information recognition device
22 Biological information database
24 Amusement store management equipment
26 Amusement table management database
27 Media lending management device
29 Media lending management database
30 Amusement store management information bus
31 Biological information bus
33 Checkout machine
34 Lending machine
35 counter
36,36-1 to 36-m game machines
37,37-1 to 37-m game console peripheral terminal
38,38-1 to 38-m camera
39,39-1 to 39- (m + p) Image processing unit
40,40-1 to 40-p In-store camera
41,41-1 to 41-q Entrance image processing unit
42,42-1 to 42-q Entrance camera
222 Verification unit
223 Unregistered Person Database Registration Department
227 Search part
232 Similarity calculator
233 Similarity determination unit
241 DB Distribution Department
242 DB update section
243 DB update judgment part
251 Unregistered Player DB
252 Registered Player DB
333 feature extraction unit
335 Similarity calculator
336 Similarity determination unit
337 Group Management Database Registration Department
338 Group management database

Claims (8)

Imaging means for capturing an image of a predetermined range at the entrance of the amusement store ;
Feature quantity extraction means for extracting the feature quantity of the face image of the person to be collated on the image captured by the imaging means;
Attribute estimation means for estimating an attribute code set by a table consisting of any one of a plurality of attribute information of the person to be collated , or a combination thereof, on the image captured by the imaging means;
Storage means for storing a face image of a registrant registered in advance in association with the attribute code ;
Among the registrants stored in association with the attribute code in the storage means, a registrant extraction means for extracting a registrant with the attribute code estimated by the estimation means;
The face image of the registrant extracted by the registrant extraction means and the face image of the person to be collated are collated based on the feature amount of the face image, and whether or not the person to be collated is the registrant. Collation determination means for determining whether or not
An information processing apparatus comprising: notification means for notifying that the verification target person is the registrant when the verification target means determines that the verification target person is the registrant. Wherein the plurality of attribute information, height, age, and an information processing apparatus according to claim 1, including gender. The attribute estimating means includes
Position acquisition means for acquiring the position of a face image of a predetermined size of the person to be collated on the image imaged by the imaging means;
The information processing according to claim 2, wherein the height of the person of the face image is estimated based on a position of the face image of a predetermined size of the person to be collated on the image acquired by the position acquisition unit. apparatus. The attribute estimating means includes
The information processing apparatus according to claim 2, wherein the age is estimated based on the feature amount extracted by the feature amount extraction unit. The attribute estimating means includes
The information processing apparatus according to claim 2, wherein the sex is estimated based on the feature amount extracted by the feature amount extraction unit. Acquisition means for acquiring a face image satisfying a predetermined search condition from the face images stored in the storage means;
A face image extracting means for extracting a reference face image and a non-reference face image among the face images acquired by the acquiring means;
Reference face image feature amount extraction means for extracting feature amounts of the reference face image ;
Non -reference face image attribute estimation means for estimating an attribute code of the non-reference face image ;
Among the non-reference face images, corresponding attribute non-reference face image extraction means for extracting only the non-reference face image having the attribute code estimated by the non-reference face image attribute estimation means;
The non-reference face image extracted by the corresponding attribute non-reference face image extraction means and the reference face image are collated based on the feature amount of the face image, and the non-reference face image is similar to the reference face image. Similarity determination means for determining whether or not
And a group registration unit for registering the non-reference face image as a group of the reference face images when the similarity determination unit determines that the non-reference face image is similar to the reference face image. Item 4. The information processing apparatus according to Item 1. An imaging step of capturing an image of a predetermined range at the entrance of the amusement store ;
A feature amount extraction step for extracting a feature amount of the face image of the person to be collated on the image captured by the processing of the imaging step;
An attribute estimation step for estimating an attribute code set by a table consisting of any one of a plurality of attribute information of the verification target person or a combination thereof on the image captured by the processing of the imaging step;
An accumulation step of accumulating a face image of a registrant registered in advance in association with the attribute code ;
A registrant extraction step of extracting a registrant having an attribute code estimated by the process of the estimation step among registrants stored in association with the attribute code in the process of the accumulation step;
The face image of the registrant extracted by the processing of the registrant extraction step and the face image of the person to be collated are collated based on the feature amount of the face image, and the person to be collated is the registrant. A collation determination step for determining whether or not,
An information processing method comprising: a notification step of notifying that the verification target person is the registrant when the verification target person is determined to be the registrant by the process of the verification determination step. An imaging step of capturing an image of a predetermined range at the entrance of the amusement store ;
A feature amount extraction step for extracting a feature amount of the face image of the person to be collated on the image captured by the processing of the imaging step;
An attribute estimation step for estimating an attribute code set by a table consisting of any one of a plurality of attribute information of the verification target person or a combination thereof on the image captured by the processing of the imaging step;
An accumulation step of accumulating a face image of a registrant registered in advance in association with the attribute code ;
A registrant extraction step of extracting a registrant having an attribute code estimated by the process of the estimation step among registrants stored in association with the attribute code in the process of the accumulation step;
The face image of the registrant extracted by the processing of the registrant extraction step and the face image of the person to be collated are collated based on the feature amount of the face image, and the person to be collated is the registrant. A collation determination step for determining whether or not,
A program for causing a computer to execute a process including a notification step of notifying that the person to be collated is the registrant when the person to be collated is determined to be the registrant by the process of the collation determining step.

Images