Admission management device, admission management system equipped with the same, and admission management program

Abstract

To provide an entry management device, an entry management system comprising the same, and an entry management program, capable of appropriately grasping and managing a fraud of an entry person after his / her entry into a game hall.SOLUTION: An entry management device 10 comprises a picture acquisition unit 11, a face detection unit 13, a face collation unit 15, a determination unit 17, and a registration unit 18. The picture acquisition unit 11 acquires a first picture imaged by a camera 21 before entry into a game hall, the first picture including a face of a first person, and second pictures imaged in the game hall after the entry into the game hall by cameras 60 to 62, the second pictures including a face of a second person. On the basis of a comparison result at the face collation unit 15, the determination unit 17 determines whether or not the first person and the second person included in the first picture and the second pictures are the same person. When it is determined by the determination unit 17 that the first person and the second person are different, the registration unit 18 registers the first person and the second person as unauthorized entry person candidates.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an entrance management device that manages visitors entering an amusement park by using an image including a person's face captured by a camera, for example, and an entrance management system equipped with the same. [Background technology]

[0002] For example, in facilities such as game parlors, there are players who visit and play games only on the opening day of a new game parlor where the game machine settings are favorable to players, or on event days where specific game machines with settings favorable to players are installed. Among these players, there are groups that visit game parlors in large numbers and secure multiple game machines with settings favorable to players. Players who visit in groups cannot be expected to visit steadily, including on regular business days. For this reason, gaming facilities do not want players who visit in groups to acquire many gaming machines with advantageous settings. Furthermore, because players who visit in groups on event days, etc., exclusively secure gaming machines with advantageous settings to play on, regular players or players who could become regulars lose the opportunity to play on gaming machines with advantageous settings, which may result in undesirable consequences for the gaming facility, such as regular players no longer visiting or players who could become regulars no longer becoming regulars.

[0003] Furthermore, in order to secure gaming machines that are set to favor players, players who come in groups often illegally obtain numbered tickets, lottery participation tickets, or admission number tickets in the lotteries held before entry on event days, etc., in order to secure an early entry spot as a group. For example, Patent Document 1 discloses that, in order to prevent such fraudulent activities, an amusement facility management device is used to photograph faces when issuing numbered tickets or lottery admission tickets, and staff visually check a list of facial images and the faces of people at the time of the lottery or entry.

[0004] However, the amusement facility management device disclosed in Patent Document 1 had a problem in that if a visitor turns his or her face away or hides it when his or her face image is captured, it becomes difficult to compare the visitor's face with a registered face image upon entry. Patent Document 2 discloses a ticket issuing device that detects the facial direction, expression, or closed eyes of an attendee, determines whether the captured facial image meets facial recognition standards, and if it is determined that the standards are not met, instructs the attendee to take a photograph again, thereby issuing a ticket on the condition that a proper facial image has been captured. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2014-23770 A [Patent Document 2] Patent No. 6428212 Summary of the Invention [Problem to be solved by the invention]

[0006] However, the ticket issuing device disclosed in Patent Document 2 places a heavy burden on staff who must visually check each visitor's face against the registered facial photograph, and there is a risk of human error, such as mistakes or oversights. Furthermore, even if it is discovered that different people have attended the lottery and at the time of entry, and the faces of resellers or fraudulent purchasers are identified from the photographs taken, this is a one-off confirmation, making it difficult to grasp the overall picture of the group, such as whether they are irregular users or not.

[0007] Furthermore, it was difficult to detect, for example, an act in which a person who was the same person at the time of the lottery and at the time of entry and who was permitted to enter the arcade gave up the seat of a gaming machine that he or she had reserved to a third party after entering the arcade. In addition, for example, if a person who has been registered in the past as a potential fraudulent entry enters an amusement facility, there is a risk that the person will commit fraud again, but once a specific person has entered the facility, it is difficult to find and report the person.

[0008] The object of the present invention is to provide an entrance management device that can properly grasp and manage unauthorized conduct by visitors after entering an amusement facility, and an entrance management system and an entrance management program equipped with the same. [Means for solving the problem]

[0009] The entrance management device according to the first invention is an entrance management device that manages visitors after they enter an amusement facility, and includes an image acquisition unit, a face detection unit, a face matching unit, a determination unit, and a registration unit. The image acquisition unit acquires a first image including a face of a first person photographed by a first imaging device before the visitor enters the amusement facility, and acquires a second image including a face of a second person photographed by a second imaging device in the amusement facility after the visitor enters the amusement facility. The face detection unit detects the facial parts of the first person and the second person included in the first image and the second image. The face matching unit compares the faces of the first person and the second person included in the first image and the second image detected by the face detection unit. The determination unit determines whether the first person and the second person included in the first image and the second image are the same person based on the result of the comparison by the face matching unit. When it is determined as a result of the determination by the determination unit that the first person and the second person included in the first image and the second image are different people, the registration unit registers the first person and the second person as candidates for unauthorized entry.

[0010] Here, whether a person before entering an amusement facility (for example, when the numbered ticket is distributed, when the lottery is drawn, or when entering) and the person after entering are swapped for another person is detected by comparing an image including the face taken before entry (first image) with an image including the face taken inside the amusement facility after entry (second image), and the people before and after the swap (first person and second person) are registered as candidates for fraudulent entry.

[0011] Here, the candidates for fraudulent entry include, for example, a transferor (first person) who transfers a seat of a gaming machine with a high setting that he / she secured after entering an amusement facility to a third party, and a transferee (second person) who enters a little later and receives the seat. In this case, it does not matter whether the transferor and the transferee are family members or acquaintances, or whether money has been handed over from the transferee to the transferor.

[0012] The image acquisition unit acquires, for example, an image including a person's face captured by a first imaging device such as a camera installed outside the game facility when distributing a numbered ticket, when a lottery is held, when entering, etc. from the first imaging device via wired or wireless communication. Similarly, the image acquisition unit acquires, for example, an image including a person's face captured by a second imaging device such as a camera installed inside the game facility after entering the game facility from the second imaging device via wired or wireless communication.

[0013] The image data acquired from the first and second imaging devices may be still image data or image data extracted from a video. The acquired first and second images are stored in a storage unit within the device, or in a server, cloud space, or the like outside the device. In addition, the first image acquired by the image acquisition unit is not limited to an image taken in front of the amusement facility when the numbered ticket is distributed, when the lottery is held, etc., but also includes an image that has already been taken and saved at a different time.

[0014] The face matching unit matches facial features used as features required to identify a person, such as the eyes, nose, mouth, eyebrows, and contours, from face-like parts contained in the first and second images detected by the face detection unit. The determination unit determines whether or not the first person and the second person are the same person based on a comparison result between the face of the first person included in the first image and the face of the second person included in the second image.

[0015] When the determination unit determines that the first person included in the first image and the second person included in the second image are different persons, the registration unit registers both the first person and the second person as candidates for unauthorized entry. This allows a first image taken before entering an amusement facility (when the numbered ticket is distributed, when the lottery is drawn, or when entering) to be compared with a second image taken inside the amusement facility after entry to detect whether the person has been replaced by a different person, and by registering the people before and after the replacement (the first person and the second person) as candidates for fraudulent entry, it becomes possible to manage people who may be fraudulent entrants. As a result, it is possible to properly grasp and manage the habitual nature of a person who may have committed a fraudulent act, such as giving up a seat on a gaming machine reserved by a first person to a second person, who is a third party, after entering an amusement facility.

[0016] The entrance management device according to the second invention is an entrance management device that manages visitors after they enter an amusement facility, and includes an image acquisition unit, a face detection unit, a face matching unit, a determination unit, and a registration unit. The image acquisition unit acquires a first image including a face of a first person previously registered as a fraudulent entry candidate, and acquires a second image including a face of a second person photographed by a second imaging device in the amusement facility after the visitor enters the amusement facility. The face detection unit detects the facial parts of the first person and the second person included in the first image and the second image. The face matching unit compares the faces of the first person and the second person included in the first image and the second image detected by the face detection unit. The determination unit determines whether the first person and the second person included in the first image and the second image are the same person based on the comparison result in the face matching unit. When it is determined as a result of the determination in the determination unit that the first person and the second person included in the first image and the second image are the same person, the registration unit registers the second person as a fraudulent entry candidate.

[0017] Here, a first image including the face of a first person previously registered as a fraudulent entry candidate is compared with a second image including the faces of an unspecified number of second people after they entered the amusement facility, and if it is determined that they are the same person, it is determined that the first person previously registered as a fraudulent entry candidate has entered the amusement facility by blending in with the unspecified number of visitors, and that person is registered again as a fraudulent entry candidate.

[0018] Here, candidates for fraudulent entry include, for example, an assignor who has previously assigned a numbered ticket or admission ticket to a third party before entering an amusement facility, an assignee who has received a numbered ticket from a third party, an assignor (first person) who assigned a seat on a high-setting gaming machine that he secured after entering an amusement facility to a third party, an assignee (second person) who entered a little later and assigned that seat, etc. At this time, it does not matter whether the assignor and assignee are family members, acquaintances, or the like, or whether or not money has been handed over from the assignee to the assignor.

[0019] The image acquisition unit acquires, for example, a first image including a face of a first person previously registered as a fraudulent entry candidate, which is stored in a memory unit provided in the entrance management device, or in an external server device, cloud space, etc., from each storage means via wired or wireless communication. Similarly, the image acquisition unit acquires, for example, an image including a face of a person captured by a second imaging device such as a camera installed in the game facility after the person enters the facility, from the second imaging device via wired or wireless communication.

[0020] The image data acquired from each storage means and the second imaging device may be still image data or image data cut out from a video. The acquired first and second images are stored in a storage unit within the device, or in a server, cloud space, or the like outside the device. The face matching unit matches facial features used as features required to identify a person, such as the eyes, nose, mouth, eyebrows, and contours, from face-like parts contained in the first and second images detected by the face detection unit.

[0021] The determination unit determines whether or not the first person and the second person are the same person based on a comparison result between the face of the first person included in the first image and the face of the second person included in the second image. When the determination unit determines that the first person included in the first image and the second person included in the second image are the same person, the registration unit re-registers the person as a candidate for unauthorized entry. This allows a first image including the face of a first person previously registered as a fraudulent entry candidate to be compared with a second image including the face of a person who has entered the amusement facility, and if a person identical to a person previously registered as a fraudulent entry candidate is detected among those who have entered the amusement facility, that person can be registered again as a fraudulent entry candidate, thereby making it possible to manage people who may be frequent fraudulent entrants.

[0022] As a result, after entering an amusement facility, the habitual nature of a person who may be a regular unauthorized entrant can be properly understood and managed.

[0023] The entrance management device of the third invention is the entrance management device of the first or second invention, further comprising a person identification unit that identifies a second person corresponding to a first person included in the first image using a plurality of second images taken by a plurality of second imaging devices installed at a plurality of locations within the amusement park. Here, for example, in order to detect fraudulent behavior such as a first person who obtains an admission ticket and enters the amusement facility giving up a seat on a gaming machine with a high setting to a third party who does not have an admission ticket after entering the amusement facility, the person identification unit identifies the second person who has replaced the first person using second images captured by multiple second imaging devices installed in the amusement facility. Here, the second person identified by the person identification unit is determined, for example, by detecting that the first person has been replaced by another person immediately after the first person sits down at a seat on the gaming machine using a second image captured by a second imaging device installed in the vicinity of the gaming machine, and identifying the replaced person as the second person. This makes it possible to effectively detect potential fraudulent entry perpetrators who, after entering an arcade, commit fraudulent acts such as giving up a seat on a gaming machine with a high setting to a third party.

[0024] An entrance management device according to a fourth aspect of the present invention is the entrance management device according to the first aspect of the present invention, wherein the image acquisition unit acquires a first image captured by a first imaging device at the time of distribution of a numbered ticket to participate in a lottery to determine the order of entry into an amusement facility, and / or at the time of the lottery, and / or at the time of entry into the amusement facility.

[0025] Here, the first image captured by the first imaging device before entry is captured at least one of when numbered tickets for participating in a lottery to determine the order of entry are distributed, when the lottery is drawn, and when entering the amusement facility. This makes it possible to obtain a first image including the face of a first person who is identified as a person who has the right to enter an amusement facility on an event day or the like, as an image taken in front of the amusement facility or the like before entry.

[0026] An entrance management device according to a fifth aspect of the present invention is an entrance management device according to the fourth aspect of the present invention, wherein the image acquisition unit acquires a second image captured by a second imaging device installed in at least one of the entrance to the amusement facility, a gaming machine installed in the amusement facility, or an inter-machine machine installed between the gaming machines. Here, the second image taken after entry into the gaming facility is captured using a second imaging device installed at least one of the entrance to the gaming facility, the gaming machine, and an inter-machine machine installed between the gaming machines. This makes it possible to obtain, for example, an image taken near the entrance when entering an amusement arcade, an image taken when sitting at a gaming machine, an image taken when operating a gaming machine, an image taken when inserting money into a gaming machine, etc. as the second image.

[0027] An entrance management device according to a sixth aspect of the present invention is an entrance management device according to any one of the first to fifth aspects of the present invention, wherein the image acquisition unit acquires a third image taken of a person seated in front of a first gaming machine when the amusement arcade opens, and a fourth image taken of the person seated in front of the first gaming machine after a predetermined time has elapsed.

[0028] Here, in order to identify a person who commits fraudulent acts after entering an amusement facility, for example, an image (third image) including the face of a person seated in front of a specific gaming machine (first gaming machine) that is highly set on an event day, etc., is captured, and then an image (fourth image) is captured again after a predetermined time (for example, five minutes) has elapsed. As a result, if the third image and the fourth image are compared and it is determined that they are different people, it can be determined that there is a high possibility that fraudulent activity has been committed, and the person in the fourth image can be registered as a suspect of fraudulent entry.

[0029] An entrance management device according to a seventh aspect of the present invention is the entrance management device according to the sixth aspect of the present invention, wherein the determination section uses the fourth image as the second image to determine the first person and the second person. Here, when it is determined that the third image and the fourth image are different people by comparing the third image and the fourth image, the fourth image is used as the second image and compared with the first image. This allows a person (second person) who has received a seat on a gaming machine from a third party through fraudulent conduct after entering the gaming facility to be registered as a fraudulent entry candidate.

[0030] An entrance management device pertaining to an eighth aspect of the present invention is the entrance management device pertaining to any one of the first to seventh aspects of the present invention, further comprising a storage unit that stores the first image and the second image. Here, a storage unit for saving the first image and the second image is provided within the device. This allows the first image and the second image to be stored in the device, and therefore when the second image captured by the second imaging device installed in the game center is acquired, the first image captured in the past can be read out from the storage unit immediately and compared with the first image.

[0031] An entrance management device according to a ninth aspect of the present invention is an entrance management device according to the eighth aspect of the present invention, wherein the memory unit stores dictionary data for matching with a first person and a second person who have been registered in the past as candidates for unauthorized entry. Here, for example, the first image, the second image, and feature amounts extracted from the first image and the second image for identifying a person are stored in the storage unit as dictionary data for future comparison with unauthorized entrants. This makes it possible to appropriately manage the habits, etc., of individuals who have been registered in the past as potential unauthorized entry candidates.

[0032] An entrance management device according to a tenth aspect of the present invention is an entrance management device according to any one of the first to ninth aspects of the present invention, further comprising a facial organ detection unit that detects specified facial organs from the facial portions of a first person and a second person contained in the first image and the second image.

[0033] Here, the face of a first person included in a first image and the facial features of a second person included in a second image are detected. Here, the facial features to be detected include, for example, the eyes, nose, mouth, eyebrows, etc. This makes it possible to take measures such as encouraging the user to take a re-shoot if the first and second images do not include all of the specified facial organs of the person's face, i.e., if the person was photographed with some of their facial organs hidden.

[0034] An entrance management device according to an eleventh aspect of the present invention is an entrance management device according to any one of the first to tenth aspects of the present invention, further comprising a face direction detection unit that detects the face direction of a first person and a second person contained in a first image and a second image. Here, the orientation of the face of a first person included in a first image and the orientation of the face of a second person included in a second image are detected. As a result, if the faces of people in the first and second images are not facing forward, measures such as encouraging the user to take a new photograph can be taken.

[0035] An entrance management device according to a twelfth aspect of the present invention is the entrance management device according to any one of the first to eleventh aspects of the present invention, further comprising a display unit that displays a list of candidates for unauthorized entry.

[0036] Here, a display unit is provided that displays a list of people registered as potential unauthorized entry candidates. This allows the administrator to easily grasp the circumstances of the fraudulent entry by looking at a display screen that lists images (first image, second image) including the faces of registered fraudulent entry candidates, the date and time of the photo, the details of the fraudulent act, etc.

[0037] The entrance management device of the 13th invention is an entrance management device of any one of the first to 12th inventions, further comprising an alarm unit that notifies an administrator that a suspected unauthorized entry registered in the registration unit is an unauthorized entry candidate when the number of times that the judgment unit has judged the suspected unauthorized entry as such exceeds a predetermined threshold value. Here, even if the first and second persons are determined to be candidates for unauthorized entry by comparing the first and second images, no immediate notification is issued. Instead, when the number of times they are determined to be candidates for unauthorized entry exceeds a predetermined threshold, an administrator (such as the amusement facility manager or store clerk) is notified of the detection of an unauthorized entrant.

[0038] Here, the threshold value used for the determination may be set to, for example, one time or three times. In this way, if a possible fraudulent entry candidate is confirmed to be a habitual fraudster, a notification can be sent to the manager of the amusement facility, etc., so that the habitual fraudulent entry candidate can be registered and managed as a fraudulent entrant.

[0039] The entrance management device according to a fourteenth aspect of the present invention is the entrance management device according to any one of the first to thirteenth aspects of the present invention, further comprising a display unit that lists and displays the unauthorized entry candidates. The unauthorized entry candidates notified by the notification unit are listed and displayed on the display unit. Here, a list of unauthorized entrants who have been notified by the notification section in the past is made and displayed on the display section. This allows the administrator to appropriately manage unauthorized entrants, whose actual circumstances are more important to understand than unauthorized entry suspects.

[0040] An entrance management system according to a fifteenth aspect of the present invention comprises an entrance management device according to any one of the first to fourteenth aspects of the present invention, a first imaging device that captures a first image, and a second imaging device that captures a second image.

[0041] Here, an entrance management system is made up of the entrance management device described above, and a first imaging device and a second imaging device that take a first image or a second image and transmit it to the entrance management device. This makes it possible to detect unauthorized entry suspects in the entrance management device using the first and second images captured by the first and second imaging devices. Therefore, management of potential unauthorized entry persons can be appropriately implemented as a system.

[0042] An entrance management system pertaining to a sixteenth aspect of the present invention is the entrance management system pertaining to the fifteenth aspect of the present invention, wherein the first imaging device and the second imaging device capture still images or video as the first image and the second image. Here, a still image or a video captured by the first imaging device or the second imaging device is used to obtain a first image and a second image used to detect a suspected unauthorized entry. This makes it possible to properly detect suspected unauthorized entry, for example, when a person is detected using a human presence sensor, or by using a still image captured by pressing a capture button, or a still image cut out from a video video from a security camera, etc.

[0043] An entrance management system according to a seventeenth aspect of the present invention is an entrance management system according to the fifteenth or sixteenth aspect of the present invention, wherein the entrance management device, the first imaging device, and the second imaging device transmit and receive various signals via wireless or wired communication. Here, the entrance management device, the first imaging device, and the second imaging device are connected via wireless or wired communication. This makes it possible, for example, to properly transmit and receive the first and second images between the entrance management device and the first and second imaging devices.

[0044] The entrance management system of the 18th invention is an entrance management system of any one of the 15th to 17th inventions, wherein the entrance management device shares information regarding suspected fraudulent entry determined using first and second images acquired from a first imaging device and a second imaging device installed in each of the multiple amusement facilities, between the multiple amusement facilities.

[0045] Here, in order to manage entrants to multiple amusement facilities, information regarding potential unauthorized entrants detected using first and second images acquired from a first and second imaging device installed in each of the multiple amusement facilities is shared among the multiple amusement facilities. This allows information about suspected fraudulent entry to be shared among multiple gaming arcades in a particular area or among multiple affiliated arcades, making it possible to appropriately identify and deal with fraudulent activities by suspected fraudulent entry.

[0046] An entrance management program according to a nineteenth aspect of the present invention is an entrance management program for managing visitors after they enter an amusement facility, and causes a computer to execute an entrance management method including a first image acquisition step, a second image acquisition step, a face detection step, a face matching step, a determination step, and a registration step. The first image acquisition step acquires a first image including a face of a first person photographed by a first imaging device before the visitor enters the amusement facility. The second image acquisition step acquires a second image including a face of a second person photographed by a second imaging device in the amusement facility after the visitor enters the amusement facility. The face detection step detects facial portions of the first person and the second person included in the first image and the second image. The face matching step compares the faces of the first person and the second person included in the first image and the second image detected in the face detection step. The determination step determines whether the first person and the second person included in the first image and the second image are the same person based on the result of the comparison in the face matching step. In the registration step, when it is determined as a result of the determination in the determination step that the first person and the second person included in the first image and the second image are different people, the first person and the second person are registered as unauthorized entry candidates.

[0047] Here, the candidates for fraudulent entry include, for example, a transferor (first person) who transfers a seat of a gaming machine with a high setting that he / she secured after entering an amusement facility to a third party, and a transferee (second person) who enters a little later and receives the seat. In this case, it does not matter whether the transferor and the transferee are family members or acquaintances, or whether money has been handed over from the transferee to the transferor.

[0048] In the first image acquisition step, for example, an image including a person's face photographed by a first imaging device such as a camera installed outside the game facility at the time of distributing a numbered ticket, at the time of a lottery, at the time of entry, etc. is acquired from the first imaging device via wired or wireless communication. Similarly, in the second image acquisition step, for example, an image including a person's face photographed by a second imaging device such as a camera installed inside the game facility after entry to the game facility is acquired from the second imaging device via wired or wireless communication.

[0049] The image data acquired from the first and second imaging devices may be still image data or image data extracted from a video. The acquired first and second images are stored in a storage unit within the device, or in a server, cloud space, or the like outside the device. In addition, the first image acquired in the first image acquisition step is not limited to an image taken in front of the amusement facility when the numbered tickets are distributed, when the lottery is held, etc., but also includes an image that has already been taken and saved at a different time.

[0050] In the face matching step, facial features used as features required to identify a person, such as the eyes, nose, mouth, eyebrows, and contours, are compared from face-like parts contained in the first and second images detected in the face detection step to determine whether they are the same person. In the determining step, it is determined whether or not the first person and the second person are the same person based on a comparison result between the face of the first person included in the first image and the face of the second person included in the second image.

[0051] In the registration step, when it is determined in the determination step that the first person included in the first image and the second person included in the second image are different persons, both the first person and the second person are registered as unauthorized entry candidates. This allows a first image taken before entering an amusement facility (when the numbered ticket is distributed, when the lottery is drawn, or when entering) to be compared with a second image taken inside the amusement facility after entry to detect whether the person has been replaced by a different person, and by registering the people before and after the replacement (the first person and the second person) as candidates for fraudulent entry, it becomes possible to manage people who may be fraudulent entrants. As a result, it is possible to properly grasp and manage the habitual nature of a person who may have committed a fraudulent act, such as giving up a seat on a gaming machine reserved by a first person to a second person, who is a third party, after entering an amusement facility.

[0052] An admission management program according to a twentieth aspect of the present invention is an admission management program for managing visitors after they enter an amusement facility, and causes a computer to execute an admission management method including a first image acquisition step, a second image acquisition step, a face detection step, a face matching step, a determination step, and a registration step. The first image acquisition step acquires a first image including a face of a first person who has been registered in the past as a fraudulent entry candidate. The second image acquisition step acquires a second image including a face of a second person photographed by a second imaging device in the amusement facility after the visit to the amusement facility. The face detection step detects facial portions of the first person and the second person included in the first image and the second image. The face matching step compares the faces of the first person and the second person included in the first image and the second image detected in the face detection step. The determination step determines whether the first person and the second person included in the first image and the second image are the same person based on the result of the comparison in the face matching step. In the registration step, when it is determined as a result of the determination in the determination step that the first person and the second person included in the first image and the second image are the same person, the second person is registered as a fraudulent entry candidate.

[0053] Here, a first image including the face of a first person previously registered as a fraudulent entry candidate is compared with a second image including the faces of an unspecified number of second people after they entered the amusement facility, and if it is determined that they are the same person, it is determined that the first person previously registered as a fraudulent entry candidate has entered the amusement facility by blending in with the unspecified number of visitors, and that person is registered again as a fraudulent entry candidate.

[0054] Here, the first person who has been registered as a candidate for fraudulent entry in the past includes, for example, an assignor who has assigned a numbered ticket or admission ticket to a third party before entering an amusement facility, an assignee who has received a numbered ticket from a third party, an assignor (first person) who assigned a seat on a high-setting gaming machine that he secured after entering an amusement facility to a third party, an assignee (second person) who entered a little later and assigned the seat, etc. At this time, it does not matter whether the assignor and assignee are family members or acquaintances, or whether there has been a transfer of money from the assignee to the assignor.

[0055] In the image acquiring step, for example, a first image including a face of a first person previously registered as a fraudulent entry candidate, which is stored in a memory unit provided in the entrance management device, or in an external server device, cloud space, etc., is acquired from each storage means via wired or wireless communication. Similarly, the image acquiring unit acquires, for example, an image including a face of a person photographed by a second imaging device such as a camera installed in the game facility after the person enters the facility, from the second imaging device via wired or wireless communication.

[0056] The image data acquired from each storage means and the second imaging device may be still image data or image data cut out from a video. The acquired first and second images are stored in a storage unit within the device, or in a server, cloud space, or the like outside the device. In the face matching step, facial features used as features required to identify a person, such as the eyes, nose, mouth, eyebrows, and contours, are matched from face-like parts contained in the first and second images detected in the face detection step.

[0057] In the determining step, it is determined whether or not the first person and the second person are the same person based on a comparison result between the face of the first person included in the first image and the face of the second person included in the second image. In the registration step, if it is determined in the determination step that the first person included in the first image and the second person included in the second image are the same person, the person is registered again as a fraudulent entry candidate.

[0058] This allows a first image including the face of a first person previously registered as a fraudulent entry candidate to be compared with a second image including the face of a person who has entered the amusement facility, and if a person identical to a person previously registered as a fraudulent entry candidate is detected among those who have entered the amusement facility, that person can be registered again as a fraudulent entry candidate, thereby making it possible to manage people who may be frequent fraudulent entrants.

[0059] As a result, after entering an amusement facility, the habitual nature of a person who may be a regular unauthorized entrant can be properly understood and managed. Effect of the Invention

[0060] According to the entrance management device of the present invention, it is possible to appropriately grasp and manage any illegal acts of visitors after entering an amusement facility. [Brief description of the drawings]

[0061] [Figure 1] 1 is a schematic diagram showing the configuration of an entrance management system including an entrance management device according to an embodiment of the present invention; [Diagram 2] FIG. 2 is a block diagram showing the configuration of the admission control system of FIG. 1. [Diagram 3] FIG. 2 is a diagram showing the flow of processing from the lottery to entry and within the amusement facility in the admission management system of FIG. 1. [Figure 4] FIG. 2 is a plan view showing an example of the arrangement of cameras installed in an amusement park. [Diagram 5] 5 is a perspective view showing the gaming machines and inter-machine machines installed in the gaming facility of FIG. 4. [Figure 6]6 is a side view showing an example of the arrangement of cameras installed in the gaming machine of FIG. 5. [Figure 7] 6A is a plan view showing an example of the arrangement of cameras installed in the gaming machine of Fig. 5. FIG. 6B is a plan view showing an example of the arrangement of cameras installed in the inter-machine of Fig. 5. [Figure 8] 2 is a diagram showing a list including facial images of people photographed by a camera included in the admission management system of FIG. 1, the photographing date and time, lottery entry number, admission order number, etc. [Figure 9] FIG. 9 shows a list of fraudulent entry candidates detected from the list of FIG. 8. [Figure 10] FIG. 10 is a diagram showing a list of unauthorized entry suspects notified to an administrator or the like from the list in FIG. 9. [Figure 11] FIG. 9 is a diagram showing a face image list created from the list in FIG. 8. [Figure 12] 2 is a diagram showing a list including face images taken before and after admission, created by the admission management system of FIG. 1. [Figure 13] 2 is a diagram showing a list including face images taken before and after admission, created by the admission management system of FIG. 1. [Figure 14] FIG. 2 is a diagram showing the overall flow of processing up to creating dictionary data by the admission management system of FIG. 1. [Figure 15] 4 is a flowchart showing the flow of processing before a lottery by the admission management system of FIG. 1. [Figure 16] 4 is a flowchart showing the flow of processing during a lottery by the admission management system of FIG. 1. [Figure 17] 4 is a flowchart showing the flow of processing at the time of admission by the admission management system of FIG. 1. [Figure 18] 4 is a flowchart showing the flow of a process of matching with previously registered fraudulent entry candidates by the entrance management system of FIG. 1; [Figure 19] 4 is a flowchart showing the flow of a process for matching with a pre-lottery image by the admission management system of FIG. 1; [Figure 20] 4 is a flowchart showing the flow of a process for matching with a lottery image by the admission management system of FIG. 1; [Figure 21]2A is a flowchart showing the flow of processing for face quality evaluation by the admission control system of FIG 1. FIG. 2B is a diagram showing Yaw, Pitch, and Roll directions used in face quality evaluation. [Figure 22] 4 is a flowchart showing the flow of a process for displaying and printing a list of suspected fraudulent entry created in the admission management system of FIG. 1. [Diagram 23] FIG. 2 is a diagram showing the overall flow of the admission control system of FIG. 1. [Figure 24] 4 is a flowchart showing the flow of detection processing after entry of a registered fraudulent entry candidate by the entrance management system of FIG. 1. [Diagram 25] 4 is a flowchart showing the flow of a process for detecting a substitution after entry by the entrance management system of FIG. 1; [Figure 26] 4 is a flowchart showing the flow of dictionary data update processing by the admission management system of FIG. 1; [Figure 27] 4 is a flowchart showing the flow of dictionary data update processing by the admission management system of FIG. 1; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0062] An entrance management device according to one embodiment of the present invention will be described below with reference to FIGS. 1 to 27. (1) Configuration of admission control system 1 The admission management system 1 of this embodiment is a system that manages people who commit fraudulent acts after an unspecified number of entrants enter an amusement facility such as a pachinko parlor, a pachislot parlor, or a casino, and mainly manages post-admission entrants who enter the amusement facility on the day the amusement facility is newly opened or on an event day when the settings of certain gaming machines are increased.

[0063] More specifically, the admission management system 1 captures images (hereinafter, facial images) including the faces of visitors at the time of distribution of the lottery participation ticket (numbered ticket), the lottery, and entry in the game center, and judges whether the person identified from the facial images matches the person at the time of distribution of the lottery participation ticket, the lottery, and entry. If the judgment result shows a mismatch, it judges that, for example, a first person who obtained the lottery participation ticket, lottery ticket, or entry order ticket (entrance ticket) has transferred the lottery participation ticket, lottery ticket, or entry order ticket to a third party (second person), and registers the first person and the second person as candidates for fraudulent entry.

[0064] Furthermore, in the admission management system 1 of this embodiment, the facial image of a person registered as a candidate for fraudulent entry is compared with facial images of an unspecified number of people who have entered to determine whether they match, and persons who have been registered as candidates for fraudulent entry in the past are detected and registered, as well as persons who have entered properly but who play games through fraudulent acts, such as handing over a gaming machine to a third party after entering, are detected and registered as candidates for fraudulent entry.

[0065] As shown in Fig. 1, the entrance management system 1 includes an entrance management device 10, a tablet terminal 20 equipped with a camera (first imaging device) 21, a ticket issuing machine 30, a barcode reader 40, a printer 50, cameras (second imaging devices) 102-104 (see Fig. 2) provided on a gaming machine 100, and a plurality of cameras (second imaging devices) 60-62 (see Fig. 2) installed in the gaming facility. The entrance management device 10, the tablet terminal 20, the ticket issuing machine 30, the barcode reader 40, the printer 50, the cameras 60-62, the gaming machine 100 (cameras 102, 103), and the inter-machine machine 110 (camera 104) are connected to each other via a wireless communication line 2 such as a wireless LAN, as shown in Fig. 2.

[0066] In addition, A in Figure 1 indicates each device installed outside the amusement facility, B indicates each device installed in the control room or the like of the amusement facility, and C indicates each device installed inside the amusement facility. The entrance management device 10 is, for example, a PC (Personal Computer) used by a manager who manages visitors to the amusement park, and acquires facial images of visitors to the amusement park taken by a camera 21 before entry (at the time of distribution of lottery participation tickets (numbered tickets), at the time of the lottery, and at the time of entry). Furthermore, the entrance management device 10 acquires facial images of visitors after entry taken by multiple cameras 60-62, 102-104 installed in the amusement park.

[0067] The entrance management device 10 then judges whether the entrant photographed before and after entry is the same person, and if it judges that there is a mismatch between the front and back face images, it registers the person in the front and back face images as a candidate for illegal entry. Furthermore, the entrance management device 10 compares the face image of the entrant after entry with face images of persons previously registered as unauthorized entry candidates, and if it determines that they match, it registers the entrant again as an unauthorized entry candidate.

[0068] The detailed configuration of the entrance management device 10 will be described later. Tablet terminal 20 is installed at a storefront or the like before entry (for example, when lottery participation tickets (numbered tickets) are distributed, when the lottery is drawn, and when entry is made), and is equipped with camera 21 that captures facial images of visitors. As shown in Fig. 1, tablet terminal 20 transmits facial images captured by camera 21 before entry to entrance management device 10 via wireless communication line 2 (see Fig. 2).

[0069] The operation of the tablet terminal 20 when photographing the face image may be performed by the visitor himself / herself while looking at the screen of the tablet terminal 20, or may be performed by a store / event staff member or the like. The camera (imaging device) 21 is a camera mounted on the tablet terminal 20 or a camera connected to the tablet terminal 20, and captures images (facial images) including the faces of visitors when lottery participation tickets (numbered tickets) are distributed, when the lottery is drawn, and when they enter the venue.

[0070] The number of face images captured by the camera 21 may be one or more. The image captured by the camera 21 may be a still image or a video. As shown in FIG. 1, the ticket issuing machine 30 is a device that prints and outputs the above-mentioned lottery participation ticket (numbered ticket) and receipt 32 serving as an admission order ticket (admission ticket) to be distributed to each visitor, and is equipped with a ticket issuing button 31.

[0071] After a facial image is captured using the camera 21 of the tablet terminal 20, the ticket issuing button 31 is operated by the visitor himself or a store staff member, etc., and the above-mentioned lottery participation ticket (numbered ticket) and a receipt 32 for the admission order ticket are issued from the ticket issuing machine 30. Here, the lottery participation ticket (numbered ticket) issued by the ticket issuing machine 30 is a receipt 32 on which a serial number is printed as numbers and a barcode. Also, the admission order ticket issued by the ticket issuing machine 30 is a receipt 32 on which an admission order number and a barcode are printed.

[0072] The day on which the lottery participation tickets and admission order tickets are issued by the ticket issuing machine 30 and the day on which the person actually enters may be the same day or different days. Furthermore, when the ticket issuing machine 30 receives a ticket issuing disabled signal, which will be described later, from the entrance management device 10, it is controlled so that a ticket cannot be issued even if the ticket issuing button 31 is pressed. The barcode reader 40 reads the barcode printed on the receipt 32 and transmits the identification signal and the like to the entrance management device 10 via the wireless communication line 2 (see FIG. 2).

[0073] This allows the entrance management device 10 to read out from the memory unit 16 a facial image corresponding to the receipt 32 from which the barcode has been read, based on the received identification signal, etc. Therefore, by reading the barcode printed on the receipt 32 and receiving the identification signal, etc. transmitted from the barcode reader 40, the entrance management device 10 can, for example, compare a facial image taken when a lottery participation ticket (numbered ticket) and / or an entrance order ticket is distributed with a facial image taken at the time of entrance to determine whether they are the same person.

[0074] The printer 50 is connected to the administrator's PC used as the entrance management device 10, and outputs, for example, a list of suspected unauthorized entry persons. In an arcade where multiple gaming machines 100 are installed, multiple cameras 60-62 are installed near entrances 120a-120c, near the counting machine 122a, the lending machine 122b, the settlement vending machine 122c, and in the corridors between island facilities 121a-121d where multiple gaming machines 100 are installed on both sides (see FIG. 4).

[0075] Cameras 102 and 103 are provided near the gaming machines 100 to capture facial images of patrons playing the gaming machines 100. Furthermore, a camera 104 is provided on an inter-machine 110 disposed adjacent to the left side of each gaming machine 100 to capture facial images of patrons playing the gaming machines 100. The number of face images captured by the cameras 60 to 62, 102 to 104 may be one or more. The images captured by the cameras 60 to 62, 102 to 104 may be still images or moving images.

[0076] (2) Configuration of the entrance management device 10 As shown in FIG. 2, the entrance management device 10 includes a display unit 10a, an image acquisition unit 11, a person identification unit 12, a face detection unit 13, a facial orientation and organ detection unit 14a, a face quality evaluation unit 14b, a face matching unit 15, a memory unit 16, a judgment unit 17, a registration unit 18, and an alarm unit 19. Here, each component of the entrance management device 10 (display unit 10a, image acquisition unit 11, person identification unit 12, face detection unit 13, facial orientation organ detection unit 14a, facial quality evaluation unit 14b, face matching unit 15, memory unit 16, judgment unit 17, registration unit 18, and notification unit 19) is a control block configured by a CPU (hardware) reading an entrance management program stored in a memory installed in the PC used as the entrance management device 10.

[0077] The display unit 10a is a display device connected to a PC used as the entrance management device 10, and displays a list including facial images taken before and after entrance, as described below, a list of suspected illegal entry, etc. The image acquiring unit 11 receives and acquires, from the tablet terminal 20, a face image taken by the camera 21 of the tablet terminal 20 before entry. Furthermore, the image acquiring unit 11 receives and acquires face images taken by a plurality of cameras 60-62, 102-104 installed in the game facility before entry.

[0078] The number of images acquired by image acquisition unit 11 may be one or more. In addition, when the images taken by camera 21 and cameras 60-62, 102-104 are moving images, image acquisition unit 11 may acquire an image including the face of a visitor cut out from the moving image, or may acquire the moving image as is. After entering the game facility, the person identification unit 12 identifies the person corresponding to the first person in the face image taken before entering the game facility, using images, videos, etc. taken by multiple cameras 60-62, 102-104 installed in the game facility.

[0079] For example, the person identification unit 12 may identify a person by tracking the movements of the people who entered in the entry order according to the admission ticket using videos or the like captured by the multiple cameras 60-62, 102-104. As a result, before the face detection process is performed in the face detection section 13, the person identification section 12 can identify the person before and after the entry.

[0080] The face detection unit 13 detects a part resembling a face from the face image acquired by the image acquisition unit 11. Note that the part resembling a face detected by the face detection unit 13 means, for example, an area detected from the face image using Haar-like features corresponding to the arrangement of facial parts (eyes, nose, mouth, etc.) and a light-dark pattern unique to a face (the difference in luminance value (contrast) between light and dark parts of an image).

[0081] The face direction and organ detection unit 14a detects the direction of a face-like part and each organ (eyes, nose, mouth, etc.) included in the face-like part included in the face image detected by the face detection unit 13. Specifically, the face direction and organ detection unit 14a detects the face direction and the face organs in order to determine whether the face-like part included in the face image is an appropriate image in which the part faces forward. The face quality evaluation unit 14b judges whether the face direction detected by the face direction and organ detection unit 14a deviates from the front by a predetermined angle or more, or whether all the predetermined face organs detected by the face direction and organ detection unit 14a are present. In other words, the face quality evaluation unit 14b judges whether the face included in the face image for which the judgment unit 17 judges whether it is the same person or not has a minimum quality required for the judgment.

[0082] Therefore, if the direction of the face detected by the face direction organ detection unit 14a deviates from the front by a predetermined angle or more, the face quality evaluation unit 14b judges that the face image is inappropriate for identifying a visitor, and takes measures such as encouraging the visitor to take a picture again, or refusing to issue a ticket or refusing entry, etc. Furthermore, if not all of the face organs detected by the face direction organ detection unit 14a are present, that is, if the face is photographed with some of the face organs hidden, the face quality evaluation unit 14b judges that the face image is inappropriate for identifying a visitor, and takes measures such as encouraging the visitor to take a picture again, or refusing to issue a ticket or refusing entry, etc., as described below.

[0083] The face matching unit 15 matches the face image determined to be appropriate by the face quality evaluation unit 14b with the face images taken before and after the entrance. The memory unit 16 stores face images taken in the amusement park before entry (when lottery participation tickets (numbered tickets) are distributed, when the lottery is drawn, and when entry is made) and after entry, which are acquired by the image acquisition unit 11. The memory unit 16 also stores a list of information such as persons registered as potential fraudulent entry candidates by past judgments and persons who have been notified as fraudulent entry, as dictionary data 16a (see FIG. 2). Furthermore, the memory unit 16 stores various programs for causing a computer to execute a visitor management method, which will be described later.

[0084] The data stored as dictionary data 16a in storage unit 16 may be edited, deleted, etc., as appropriate by an administrator, etc. As for the face image stored in dictionary data 16a, for example, only one representative face image may be stored together with feature amounts calculated using a plurality of face images captured at one time. The judgment unit 17, for example, compares a facial image (first image) before entry (at the time the lottery participation ticket is distributed, at the time of the lottery, at the time of entry) stored in the memory unit 16 as dictionary data 16a with a facial image (second image) taken by cameras 60-62, 102-104 after entry to judge whether the facial images are of the same person.

[0085] Here, to determine whether the faces contained in the two facial images match, for example, the facial features extracted to identify a person are compared between the two facial images to calculate the similarity, and if the calculated similarity is greater than a predetermined threshold, it is determined that they are the same person, and if it is equal to or less than the predetermined threshold, it is determined that they are different people. The facial features are calculated based on a plurality of feature points (e.g., facial organs such as eyes, nose, nostrils, mouth, eyebrows, chin, forehead, etc.) located in face-like areas detected by face detection unit 13, and are calculated using values ​​obtained by filtering using, for example, a Gabor filter.

[0086] The arrangement of the feature points may be set differently depending on the age and sex of the person in the face image. Furthermore, the determination unit 17 compares a face image (first image) of a person (first person) previously registered as a fraudulent entry candidate with a face image (second image) of a person (second person) photographed by the cameras 60-62, 102-104 after entry to determine whether they match. This makes it possible to determine whether a person previously registered as a fraudulent entry candidate has visited the venue again or is a habitual fraudster.

[0087] Furthermore, based on the judgment result in the face quality evaluation unit 14b, the judgment unit 17 judges whether or not the face image contained in the face image captured by the camera 21 at the time of distributing the lottery participation ticket, at the time of the lottery, and at the time of entry is appropriate, and also judges whether or not the lottery participation ticket or the entry sequence ticket can be issued in the ticket issuing machine 30. In other words, if the face quality evaluation unit 14b determines that the facial orientation and the presence or absence of organs contained in the facial image do not satisfy predetermined conditions, or if it determines that there is a high possibility that the person is the same person as a previously registered candidate for unauthorized entry, or if it determines that the compared facial image is a mismatch and there is a high possibility that the person is a different person, the judgment unit 17 sends a ticket issuance disallowance signal to the ticket issuing machine 30 to prevent the issuance of a lottery participation ticket or admission order ticket to the person whose facial image was captured.

[0088] As a result, when the ticket issuing machine 30 receives a ticket issuing disabled signal from the entrance management device 10, it is controlled so that a ticket cannot be issued even if the ticket issuing button 31 is operated. As a result, for example, it is possible to prevent entry at the ticket issuing stage for people who may be unauthorized entrants who intentionally do not allow a proper face image to be captured, people who have been registered in the past as candidates for unauthorized entry, and people who have received a lottery ticket from a third party.

[0089] The registration unit 18, in the judgment unit 17, for example, compares face images taken at the time of distribution of lottery participation tickets and at the time of the lottery with face images taken by the camera 21 at the time of entry, and if it is judged that the three face images are not of the same person, it registers the face images of those persons as candidates for illegal entry. Specifically, the registration unit 18 stores information such as the face images and the photographed dates and times of those persons in the dictionary data 16a of the storage unit 16 as candidates for unauthorized entry.

[0090] Furthermore, the registration unit 18, in the judgment unit 17, for example, compares a face image taken before entry with a face image taken in the gaming facility after entry, and if it detects that the corresponding person has been replaced by a different person after entry, in other words, that the gaming machine 100 has been handed over to a third party after proper entry, then registers the person as a candidate for fraudulent entry. Furthermore, when the determination unit 17 detects that a person entered the game facility on the same day as a person previously registered as a fraudulent entry candidate, the registration unit 18 registers the person as a fraudulent entry candidate.

[0091] Specifically, the registration unit 18 stores the fraudulent entry candidates in the storage unit 16 as dictionary data 16a. When a person registered by the registration unit 18 as a fraudulent entry candidate has been registered a number of times greater than a preset threshold, the notification unit 19 notifies the manager of the amusement facility or store staff, etc., that a fraudulent entrant has entered the facility.

[0092] This allows a manager, store staff, etc. to recognize that a potential unauthorized entrant has entered the store and take measures such as asking the person to leave or giving a warning. As a method of notification by the notification unit 19, for example, a message such as "The arrival of a suspected unauthorized entry has been detected" may be displayed on the display unit 10a of the entrance management device 10, or an alert sound may be sounded to notify store staff, etc.

[0093] Furthermore, in the entrance management device 10 of this embodiment, the notification unit 19 issues a notification when the number of times a person has been registered as a fraudulent entry candidate exceeds a predetermined number. This means that measures such as asking a person to leave, reporting them, or giving them a warning can only be taken if it is determined that the person has a habitual history of illegal entry.

[0094] <Process from distribution of lottery entry tickets to entry> In the admission management system 1 of this embodiment, processes from distribution of lottery participation tickets to admission and processes after admission are carried out in accordance with the flow shown in FIG. That is, in the first stage before the lottery, customers who come to the arcade line up in front of the arcade to participate in the lottery that determines the order of entry. At this time, camera 21 is constantly photographing visitors, and when a visitor's face is detected in the photographed image and the facial orientation and facial features satisfy predetermined conditions, a store staff member of the amusement arcade or an event staff member brought in on the day of the event presses ticket issuance button 31, a signal permitting the issuance of a lottery participation ticket is sent to ticket issuing machine 30, and a lottery participation ticket with a serial number and barcode attached is distributed to the customer by the store staff member or the like.

[0095] This allows lottery tickets to be issued only when a face image that satisfies the conditions required for identifying a person can be acquired. Also, compared to when a face image is taken and processing such as face detection is performed after the ticket issue button 31 is pressed, it is not necessary to take a face image again and again when a face image that does not satisfy the necessary conditions is taken, so processing can be made more efficient.

[0096] Next, in the second stage of the lottery, customers line up in the order of the serial numbers attached to their lottery tickets. Then, a store staff member or the like reads the barcode attached to the lottery ticket using a barcode reader 40 and transmits the obtained identification signal to the entrance management device 10. Then, in the entrance management system 1, as in the first stage, the camera 21 constantly photographs visitors, and when a visitor's face is detected in the photographed image and the facial orientation and facial features satisfy predetermined conditions, the facial images of the customers who are present at the time of the lottery are photographed to hold a lottery to determine the order of admission. Next, the entrance management device 10 reads out the facial images before the lottery that are linked to the identification number based on the barcode and stored in the memory unit 16, and compares the facial images before the lottery with the facial images at the time of the lottery.

[0097] If the face image before the lottery and the face image at the time of the lottery match, it is determined that there was no illegal entry, and an entry order ticket with a barcode and the entry order determined by the lottery is distributed to the customer by a store staff member or the like. On the other hand, if there is a mismatch between the facial image before the lottery and the facial image at the time of the lottery, it is determined that there is a high possibility of fraudulent entry because the person who received the lottery ticket (transferee) is different from the person at the time of the lottery (transferor), and the person is registered as a suspected fraudulent entry, or an alert notification (notification) is sent to an administrator, etc.

[0098] Next, in the third stage of admission, customers line up in the admission order given on their admission order tickets. Then, a store staff member or the like reads the barcode given on the admission order ticket using a barcode reader 40 and transmits the obtained identification signal to the admission management device 10. The entrance management device 10 photographs the face images of customers who enter the venue, reads out the face images taken before and at the time of the lottery, which are linked to the identification number based on the barcode and stored in the memory unit 16, and compares the face images taken before and at the time of the lottery with the face images taken at the time of entrance.

[0099] If the facial image before and at the time of the lottery matches the facial image at the time of entry, it is determined that the entry was not unauthorized, and the customer is permitted to enter. On the other hand, if there is a mismatch between the facial image before and at the time of the lottery and the facial image at the time of entry, it is determined that there is a high possibility of fraudulent entry, in that the person who received the entry turn ticket is a different person from the person before and at the time of the lottery, and the person is registered as a suspected fraudulent entry, or an alert notification (notification) is sent to an administrator, etc.

[0100] The entrance management system 1 then lists the facial images, registration information, abandonment history, etc. of the people (transferors and transferees) registered as unauthorized entry candidates, and outputs them from the display unit 10a or the printer 50. The information registered here is stored in the memory unit 16 as dictionary data 16a for matching with facial images photographed within the amusement facility. Next, in processing after entry into the gaming facility, facial images (second images) of the entrant are captured by cameras 60a, 60b, 60c (see Figure 4) installed near the entrance to the gaming facility, cameras 102, 103 (see Figure 4) that photograph the entrant seated in front of the gaming machine 100, camera 104 (see Figure 4) installed on the inter-machine machine 110 that photographs the entrant when he or she makes a deposit, and cameras 102, 103 that photograph the entrant when he or she starts playing on the gaming machine 100.

[0101] As shown in FIG. 4, cameras 60a-60c, 61a-61c, 62a-62d are installed in the amusement park to monitor the behavior of visitors within the amusement park, such as visitors entering through entrances 120a-120c, visitors playing on the gaming machines 100 included in the island equipment 121a-121d, and visitors using the counting machine 122a, the rental machine 122b, and the settlement vending machine 122c.

[0102] The counter 122a counts the number of gaming media acquired by spectators playing the gaming machines 100, and outputs the count result on a magnetic card, receipt, or the like. When a spectator plays on the gaming machine 100, the lending machine 122b accepts a predetermined amount of money in the form of cash, a prepaid card, or the like, and lends out a number of gaming media according to the amount. The settlement vending machine 122c sells prepaid cards with points for borrowing game media. The settlement vending machine 122c also settles and dispenses cash according to the remaining number of game media lent as points on the prepaid card or the like.

[0103] A predetermined number of gaming machines 100 are installed on each of the island facilities 121a to 121d. The gaming machines 100 are operated by visitors to play games, and pay out gaming media such as game balls and medals depending on whether a small win or a big win occurs. At this time, as shown in Fig. 5, when a big win or the like occurs during play, the corresponding machine indicator lamps 101a to 101c installed directly above the gaming machines 100a to 100c light up or flash.

[0104] The inter-machine machines 110a, 110b are installed between the gaming machines 100a to 100c as shown in Fig. 5, and like the lending machine 122b, when a spectator plays on the gaming machine 100, they accept a predetermined amount of money by inserting cash, a prepaid card, or the like, and lend out a number of gaming media according to the amount. In the example shown in Fig. 5, the inter-machine machines 110 are installed between each of the three gaming machines 100a to 100c, but basically, one is installed on the left side of each gaming machine 100.

[0105] As shown in FIG. 4, cameras 60a to 60c are installed at positions that allow them to photograph entrances 120a to 120c from within the game facility, and photograph people entering and leaving. The cameras 61a to 61c are arranged near the respective devices in order to capture images of visitors operating the counting machine 122a, the lending machine 122b, and the settlement vending machine 122c. The cameras 62a to 62d are installed in a row along the passage between the island facilities 121a to 121d, on both sides of which a predetermined number of gaming machines 100 are installed, in order to capture images of visitors moving along the passage.

[0106] Each of the cameras 60a to 60c, 61a to 61c, and 62a to 62d has a pan-tilt-zoom function, and therefore, using these cameras 60a to 60c, 61a to 61c, and 62a to 62d, it is possible to capture images of all visitors playing on the gaming machines 100 in the gaming arcade. 6, a camera 102 capable of photographing the face of a visitor P1 playing a game is installed below the machine indicator lamp 101 provided at the top of each gaming machine 100. This makes it possible to photograph the face of a visitor P1 who is seated in front of the gaming machine 100 and playing a game, in addition to photographing visitors moving around the gaming facility.

[0107] As a camera for photographing the face of the spectator P1 while playing, as shown in Fig. 7(a), a camera 103 installed inside the gaming machine 100 may be used to photograph the face of the spectator P1 from the front while playing. Alternatively, as shown in Fig. 7(b), a camera 104 provided on an inter-machine 110 installed on the left side of each gaming machine 100 may be used to photograph the face of the spectator P1 while playing from a slightly oblique angle.

[0108] In addition, the cameras 102, 103 installed directly above or inside the gaming machine 100 may start shooting, for example, when a gaming medium is detected by an out ball counter 105 installed at the bottom of each gaming machine 100. The out ball counter 105 is provided at the bottom inside of each gaming machine 100 in order to count the number of gaming media that are discharged without winning in the winning port among the gaming media that are shot out when the game starts. The out ball counter 105 transmits information regarding the counted number of gaming media to an island equipment management device (not shown).

[0109] This allows the spectator P1 to be photographed while facing the gaming machine 100 and playing the game, so that the face of the spectator P1 can be photographed from the front. In addition, the camera 104 installed in the space-between machine 110 provided on the left side of the gaming machine 100 may start taking pictures, for example, when the deposit detection unit 106 detects that cash or a prepaid card has been inserted into the space-between machine 110.

[0110] This allows visitor P1 to be photographed while facing the inter-unit machine 110 and performing the deposit operation, so that the face of visitor P1 can be photographed from the front. Each of the cameras 60a to 60c, 61a to 61c, 62a to 62d, and 102 to 104 installed inside the game facility transmits the captured images (still images or video images) to the entrance management device 10.

[0111] The facial images stored in the memory unit 16 are stored in a list, for example, as shown in FIG. 8, together with images taken before entry (before the lottery (when the lottery participation tickets are distributed), at the time of the lottery, and at the time of entry), together with data such as the lottery participation number, the date and time of the photo taken before the lottery, the entry order number, the date and time of the photo taken at the lottery, and the date and time of the photo taken at the time of entry. Then, the determination unit 17 uses the list of FIG. 8 stored in the storage unit 16 to compare the face images taken at three stages (before the lottery, at the time of the lottery, and at the time of entry) and determines whether or not they match.

[0112] For example, in the example of Figure 8, the person with lottery participation number 00002 is different before and at the time of the lottery, but is the same at the time of the lottery and when they enter. Therefore, it is highly likely that a person who obtained a lottery participation ticket before the lottery transferred (including reselling) the lottery participation ticket to a third party, and that a person who received the lottery participation ticket (including fraudulent purchase) participated in the lottery and entered. For this reason, in the entrance management device 10, the registration unit 18 registers the facial image of the person before the lottery (solid line) and the facial image of the person at the time of the lottery (at the time of entry) (dashed line) as candidates for fraudulent entry, and stores them as dictionary data 16a in the memory unit 16.

[0113] Similarly, in the example of Fig. 8, the person with lottery participation number 00105 matches the person before and at the time of the lottery, but does not match the person at the time of the lottery and when they entered. For this reason, it is highly likely that a person who obtained a lottery participation ticket before the lottery and participated in the lottery transferred (including reselling) the admission order ticket to a third party, and that a person who received the admission order ticket (including fraudulent purchase) entered the venue. For this reason, in the entrance management device 10, the registration unit 18 registers the facial image of the person at the time of the lottery (before the lottery) (solid line) and the facial image of the person at the time of entry (dashed line) as candidates for fraudulent entry, and stores them as dictionary data 16a in the memory unit 16.

[0114] 8, the facial images of the people with lottery participation numbers 00001, 00003, and 00106 before the lottery, at the time of the lottery, and at the time of entry all match. Therefore, the determination unit 17 of the entrance management device 10 determines that these people are not candidates for unauthorized entry. Then, for the suspected fraudulent entry stored in the memory unit 16 as dictionary data 16a, as shown in FIG. 9, the dictionary number, registration date and time, type of fraudulent activity (transfer, acceptance), number of reports, and comment (content of fraudulent activity) are stored in a list together with the facial image.

[0115] For example, the person with dictionary number 0001 is a potential fraudulent entrant who was registered at 08:32 on 2019 / 6 / 10, and is registered as having committed fraudulent acts by transferring a lottery ticket to a third party, and is registered as having been reported to the administrator, etc., as suspected fraudulent entrants three times in the past. Therefore, the person with dictionary number 0001 is highly likely to be a habitual perpetrator of fraudulent entrants. On the other hand, the person with dictionary number 0004 is a potential fraudulent entrant who was registered at 08:45 on 2019 / 6 / 10, and is registered as having committed fraudulent acts by receiving an admission ticket from a third party, and is also registered as having been reported to the administrator once in the past as a suspected fraudulent entrant. Therefore, the person with dictionary number 0004 may become a habitual perpetrator of fraudulent entrants in the future.

[0116] In addition, individuals who have a history of being reported to an administrator or the like as unauthorized entrants are treated as habitual offenders requiring surveillance, and their facial image is stored in a list along with the report dictionary number, type of unauthorized activity (transfer, transfer), and the date and time of the report, as shown in Figure 10. For example, the person with notification dictionary number 0002 is a potential fraudulent entry candidate who was registered on 2019 / 6 / 10 at 08:32, and is registered as having committed fraudulent conduct by receiving an entry order ticket from a third party.

[0117] The determination of whether the facial images match or not in the determination unit 17 may be performed using a facial image list shown in FIG. Specifically, as shown in FIG. 11, the face image list includes a lottery entry number, a face image before the lottery, an entrance order, a face image at the time of the lottery, and a face image at the time of entrance. This allows the determination unit 17 of the entrance management device 10 to easily determine whether or not all of the facial images taken at three stages - before the lottery, at the time of the lottery, and at the time of entrance - are of the same person.

[0118] The list of unauthorized entry candidates shown in FIG. 11 is used as dictionary data (a list of unauthorized entry candidates previously registered) to be checked when making a determination to detect unauthorized entry candidates after entry, which will be described later. Here, in the entrance management device 10 of this embodiment, in order to compare a facial image (first image) captured by the camera 21 before entry (at the time of entry) with a facial image (second image) of a person after entry corresponding to the person in this facial image, a list including the entrance order number, the pre-entry (at the time of entry) image, the post-entry image, and the type of fraudulent activity is created and stored in the memory unit 16, as shown in FIG. 12.

[0119] For example, in the example shown in FIG. 12, it can be seen that the person with the entrance sequence number 00008 has switched positions before and after entrance. As a result, by simply creating the list shown in FIG. 12 and comparing facial images before and after entry, it is possible to easily detect the person who entered with entry sequence number 00008 (first person) and the person who, for example, replaced him / her after entry and handed over the gaming machine 100 with a higher setting (second person), and to register both of these people as candidates for fraudulent entry.

[0120] Furthermore, in the entrance management device 10 of this embodiment, using the list shown in FIG. 13, a person who was previously registered as a fraudulent entry candidate is detected as entering an amusement facility using a facial image taken after entry, and the person is re-registered as a fraudulent entry candidate. The list shown in FIG. 13 includes the dictionary number, face images of suspected fraudulent entry, the date and time of registration, the type of fraudulent act, the number of times of notification, face images detected within the amusement facility, and the date and time of the photograph taken within the facility.

[0121] As a result, as shown in Figure 13, when a person who has previously been registered as a suspected fraudulent entry is detected using a facial image taken within the amusement facility, the person can be re-registered in a list along with the date and time of registration, the type of fraudulent activity (transfer, acceptance), and the number of times it was reported. As a result, for example, a manager or store staff member can be notified of the entry of a person registered as a possible unauthorized entry suspect, and measures such as expulsion or a warning can be taken.

[0122] <Admission management method using admission management system 1> In the entrance management system 1 of this embodiment, first, an entrance management method is implemented in accordance with the flowcharts shown in Figs. 14 to 22, in which a list of people who have been registered in the past as candidates for unauthorized entry is created before entry to an amusement facility. That is, as shown in FIG. 14, the entrance management system 1 mainly executes a pre-lottery process S1, a lottery process S2, an entrance process S3, and a list display and printing process S4 as an overall flow before entrance.

[0123] The contents of each of the processes S1 to S4 will be described in detail below. <Pre-lottery processing> The process S1 before the lottery is carried out according to the flowchart shown in FIG. First, in step S11, a decision is made as to whether or not to continue processing until there are no more visitors waiting in line to obtain a lottery participation ticket before the lottery drawing or until a predetermined number of lottery participation tickets have been distributed, and the decision as to whether to continue processing is repeated until distribution to everyone is complete or the predetermined number of lottery participation tickets have been distributed.

[0124] Next, in step S12, a facial image of the person to whom the lottery participation ticket is distributed is captured using the camera 21 of the tablet terminal 20. The captured facial image is then immediately transmitted from the tablet terminal 20 to the entrance management device 10, and is received by the image acquisition unit 11 of the entrance management device 10. Next, in step S13, the face detection unit 13 of the entrance management device 10 detects a part that resembles a face included in the face image acquired by the image acquisition unit 11.

[0125] Next, in step S14, it is determined whether or not a face-like portion has been detected by the face detection unit 13. If a face-like portion has been detected, the process proceeds to step S15. On the other hand, if a face-like portion has not been detected, the process returns to step S12, and a message prompting the user to retake a face image is displayed on the tablet terminal 20 or the like. Next, in step S15, the face direction and organ detection unit 14a of the entrance management device 10 detects the face direction and facial organs from the face-like parts.

[0126] Next, in step S16, the face quality evaluation unit 14b of the entrance management device 10 judges whether the face image is of a quality that can withstand the judgment unit 17 as to whether it is the same person or not, depending on the face direction and the presence or absence of organs detected by the face direction and organ detection unit 14a. The face quality evaluation process in step S16 will be described in detail later. Next, in step S17, it is determined whether the facial quality evaluation unit 14b judges that the facial quality is OK. If the facial quality is OK, the process proceeds to step S18. On the other hand, if the facial quality is NG, the process returns to step S12, and a message prompting the user to retake a facial image is displayed on the tablet terminal 20 or the like.

[0127] Next, in step S18, the face image whose face quality has been determined to be OK is stored in the face image database of the storage unit 16. Next, in step S19, the face matching unit 15 matches face images of previously registered fraudulent entry candidates stored as dictionary data 16a in the storage unit 16 with the face image photographed before the lottery. Note that the detailed process of step S19 will be described later in the process of matching with registered fraudulent entry candidates.

[0128] Next, in step S20, the determination unit 17 determines whether or not the facial images of the fraudulent entry candidates previously registered in the face matching unit 15 match the facial images taken before the lottery. If there is a match, the person may be a habitual illegal entrant, and the process proceeds to step S21. On the other hand, if there is no match, the person is not a habitual illegal entrant, and the process proceeds to step S23.

[0129] Next, in step S21, since the determination in step S20 indicates a match, the unauthorized entry flag is turned ON. Next, in step S22, it is determined whether or not the number of times the person has been registered as a fraudulent entry candidate is greater than a predetermined threshold value Th1. Here, if the number of times that the person has been registered as a candidate for fraudulent entry is already greater than the threshold value Th1, the process proceeds to step S26, in which the entrance management device 10 sends a ticket disabling signal to the ticket issuing machine 30, and in step S27, an alert is sent to the manager, store staff of the amusement facility, etc.

[0130] This makes it possible to prohibit distribution of lottery participation tickets to persons who have a history of being registered as candidates for unauthorized entry in the past, and to prevent in advance the entry of persons who have a history of being registered as candidates for unauthorized entry. Furthermore, managers and store staff can take measures such as refusing entry to individuals who have a history of being registered as potential unauthorized entry perpetrators, or warning them to stop unauthorized entry.

[0131] On the other hand, if the number of times is equal to or less than the predetermined threshold value Th1, the manager and store staff are not notified, and the process proceeds to step S23. Next, in step S23, since the person has no history of being registered as a fraudulent entry candidate, or the number of times the person has been registered is equal to or less than the predetermined threshold value Th1, a lottery participation number is assigned to the person. Next, in step S24, the ticket issuing machine 30 issues a lottery participation ticket having a lottery participation number and a barcode attached thereto.

[0132] Next, in step S25, the face image linked to the lottery participation ticket number is stored in the storage unit 16. In the pre-lottery processing, the above-mentioned steps S11 to S26 are repeated until there are no more visitors waiting in line to obtain pre-lottery lottery participation tickets, or until a predetermined number of lottery participation tickets have been distributed.

[0133] <Lottery process> Next, the lottery process S2 is carried out according to the flowchart shown in FIG. First, in step S31, it is determined whether or not to continue the process until there are no more visitors holding lottery participation tickets in line, and the determination as to whether or not to continue the process is repeated until the lottery for all visitors has been completed.

[0134] Next, in step S32, the barcode reader 40 reads the barcode attached to the lottery participation ticket distributed before the lottery and transmits the obtained identification information to the entrance management device 10, and the judgment unit 17 of the entrance management device 10 reads out the facial image linked to the lottery participation number and stored in the memory unit 16. Next, in step S33, a facial image of a person participating in the lottery is captured using the camera 21 of the tablet terminal 20. The captured facial image is then immediately transmitted from the tablet terminal 20 to the entrance management device 10, and is received by the image acquisition unit 11 of the entrance management device 10.

[0135] Next, in step S34, the face detection section 13 of the entrance management device 10 detects a part that resembles a face included in the face image acquired by the image acquisition section 11. Next, in step S35, it is determined whether or not a part resembling a face has been detected by the face detection unit 13. If a part resembling a face has been detected, the process proceeds to step S36. On the other hand, if a part resembling a face has not been detected, the process returns to step S33, and a message prompting the user to retake a face image is displayed on the tablet terminal 20 or the like.

[0136] Next, in step S36, the face direction and organ detection unit 14a of the entrance management device 10 detects the face direction and the facial organs from the face-like parts. Next, in step S37, the face quality evaluation unit 14b of the entrance management device 10 judges whether the face image is of a quality that can withstand the judgment unit 17 as to whether it is the same person or not, depending on the face direction and the presence or absence of organs detected by the face direction and organ detection unit 14a.

[0137] The face quality evaluation process in step S37 will be described in detail later. Next, in step S38, it is determined whether the facial quality evaluation unit 14b judges that the facial quality is OK. If the facial quality is OK, the process proceeds to step S39. On the other hand, if the facial quality is NG, the process returns to step S33, and a message prompting the user to retake a facial image is displayed on the tablet terminal 20 or the like.

[0138] Next, in step S39, the face image whose face quality has been determined to be OK is stored in the face image database of the storage unit 16. Next, in step S40, the face matching unit 15 matches face images of previously registered fraudulent entry candidates stored as dictionary data 16a in the storage unit 16 with the face image photographed at the time of the lottery. Note that the detailed processing of step S40 will be explained in the process of matching with registered fraudulent entry candidates described later.

[0139] Next, in step S41a, the determination unit 17 determines whether or not the facial images of the fraudulent entry candidates previously registered in the face matching unit 15 match the facial images taken before the lottery. If there is a match, the person may be a habitual illegal entrant, and the process proceeds to step S42a. On the other hand, if there is no match, the person is not a habitual illegal entrant, and the process proceeds to step S45.

[0140] Next, in step S42a, since the determination in step S41a indicates a match, the unauthorized entry flag is set to ON. Next, in step S43a, it is determined whether the number of times the person has been registered as a fraudulent entry candidate is greater than a predetermined threshold value Th1. Here, if the number of times that the person has been registered as a candidate for fraudulent entry is already greater than the threshold value Th1, the process proceeds to step S49, in which the entrance management device 10 sends a ticket disabling signal to the ticket issuing machine 30, and in step S50, an alert is sent to the manager, store staff of the amusement facility, etc.

[0141] This makes it possible to prohibit distribution of admission order tickets to persons who have a history of being registered as unauthorized entry candidates in the past, and to prevent in advance the admission of persons who have a history of being registered as unauthorized entry candidates. Furthermore, managers and store staff can take measures such as refusing entry to individuals who have a history of being registered as potential unauthorized entry perpetrators, or warning them to stop unauthorized entry.

[0142] On the other hand, if the number of times is equal to or less than the predetermined threshold value Th1, the manager and store staff are not notified, and the process proceeds to step S44. Next, in step S44, since the person has no history of being registered as a fraudulent entry candidate, or the number of times the person has been registered is equal to or less than the predetermined threshold value Th1, the flag that was set to ON in step S42a is set to OFF.

[0143] Next, in step S45, the face matching unit 15 matches the face images captured before and at the time of the lottery. The matching process of the face image captured before the lottery and the face image captured at the time of the lottery in step S45 will be described in detail later. Next, in step S41b, the determination unit 17 determines whether or not the face image captured before the lottery and the face image captured at the time of the lottery match in the face matching unit 15.

[0144] If they do not match, the lottery ticket may have been transferred to a third party, so the process proceeds to step S42b. On the other hand, if they match, there is no possibility of unauthorized entry, so the process proceeds to step S46. Next, in step S42b, since it was determined in step S41b that the facial images before and at the time of the lottery did not match, the unauthorized entry flag is set ON.

[0145] Next, in step S43b, it is determined whether or not the number of times the person has been registered as a fraudulent entry candidate is greater than a predetermined threshold value Th1. Here, if the number of times that the person has been registered as a candidate for fraudulent entry is already greater than the threshold value Th1, the process proceeds to step S49, in which the entrance management device 10 sends a ticket disabling signal to the ticket issuing machine 30, and in step S50, an alert is sent to the manager, store staff of the amusement facility, etc.

[0146] This makes it possible to prohibit distribution of admission order tickets to persons who have a history of being registered as unauthorized entry candidates in the past, and to prevent in advance the admission of persons who have a history of being registered as unauthorized entry candidates. Furthermore, managers and store staff can take measures such as refusing entry to individuals who have a history of being registered as potential unauthorized entry perpetrators, or warning them to stop unauthorized entry.

[0147] On the other hand, if the number of times is equal to or less than the predetermined threshold value Th1, the manager and store staff are not notified, and the process proceeds to step S46. Next, in step S46, since the person has no history of being registered as a candidate for unauthorized entry and whose face image matches that before and at the time of the lottery, or whose number of registrations is less than or equal to a predetermined threshold value Th1, the person is given an entry order.

[0148] Next, in step S47, the ticket issuing machine 30 issues an admission order ticket with the admission order number and a barcode attached thereto. Next, in step S48, the face image linked to the lottery participation number and the admission order is stored in the storage unit 16. In the lottery process, the above-mentioned steps S31 to S49 are repeated until there are no more visitors who wish to participate in the lottery.

[0149] <Admission process> Next, the entrance process S3 is carried out according to the flowchart shown in FIG. First, in step S51, it is determined whether or not to continue the process until there are no more visitors holding admission order tickets in line, and the determination as to whether to continue the process is repeated until all visitors holding admission order tickets have entered.

[0150] Next, in step S52, the barcode reader 40 reads the barcode attached to the admission order ticket distributed at the time of the lottery and transmits the obtained identification information to the admission management device 10, and the judgment unit 17 of the admission management device 10 reads out the facial images before and at the time of the lottery that are linked to the admission order and stored in the memory unit 16. Next, in step S53, a facial image of a person entering the game facility is captured using the camera 21 of the tablet terminal 20. The captured facial image is then immediately transmitted from the tablet terminal 20 to the entrance management device 10, and is received by the image acquisition unit 11 of the entrance management device 10.

[0151] Next, in step S54, the face detection section 13 of the entrance management device 10 detects a part that resembles a face included in the face image acquired by the image acquisition section 11. Next, in step S55, it is determined whether or not a part resembling a face has been detected by the face detection unit 13. If a part resembling a face has been detected, the process proceeds to step S56. On the other hand, if a part resembling a face has not been detected, the process returns to step S53, and a message prompting the user to retake a face image is displayed on the tablet terminal 20 or the like.

[0152] Next, in step S56, the face direction and organ detection unit 14a of the entrance management device 10 detects the face direction and facial organs from the face-like parts. Next, in step S57, the face quality evaluation unit 14b of the entrance management device 10 judges whether the face image is of a quality that can withstand the judgment unit 17 as to whether it is the same person or not, depending on the face direction and the presence or absence of organs detected by the face direction and organ detection unit 14a.

[0153] The face quality evaluation process in step S57 will be described in detail later. Next, in step S58, it is determined whether the facial quality evaluation unit 14b judges that the facial quality is OK. If the facial quality is OK, the process proceeds to step S59. On the other hand, if the facial quality is NG, the process returns to step S53, and a message prompting the user to retake a facial image is displayed on the tablet terminal 20 or the like.

[0154] Next, in step S59, the face image whose face quality has been determined to be OK is stored in the face image database of the storage unit 16. Next, in step S60, face matching unit 15 matches face images of previously registered unauthorized entry candidates stored as dictionary data 16a in storage unit 16 with the face image photographed at the time of entry. Note that detailed processing of step S60 will be explained in the process of matching with registered unauthorized entry candidates described later.

[0155] Next, in step S61, the determination unit 17 determines whether or not the facial images of candidates for unauthorized entry previously registered in the face matching unit 15 match the facial images taken before the lottery. If there is a match, the person may be a habitual illegal entrant, and the process proceeds to step S62. On the other hand, if there is no match, the person is not a habitual illegal entrant, and the process proceeds to step S64.

[0156] Next, in step S62, since the determination in step S61 indicates a match, the unauthorized entry flag is set to ON. Next, in step S63, it is determined whether the number of times the person has been registered as a fraudulent entry candidate is greater than a predetermined threshold value Th1. Here, if the number of times that a person has been registered as a fraudulent entry candidate is already greater than the threshold value Th1, the process proceeds to step S69, where a notice is sent to the manager, store staff of the amusement facility, etc. This allows the manager and store staff to take measures such as refusing entry to a person who has a history of being registered as a fraudulent entry candidate as a habitual fraudulent entry perpetrator, or warning the person to stop fraudulent entry.

[0157] On the other hand, if the number of times is equal to or less than the predetermined threshold value Th1, the manager and store staff are not notified, and the process proceeds to step S64. Next, in step S64, since the person has no history of being registered as a fraudulent entry candidate, or the number of times the person has been registered is equal to or less than the predetermined threshold value Th1, the flag that was set to ON in step S62 is set to OFF.

[0158] Next, in step S65, the face matching unit 15 matches the face with the face images captured before and at the time of the lottery. Next, in step S66, the determination unit 17 determines whether or not the face image captured at the time of the lottery and the face image captured at the time of entry are matched by the face matching unit 15. If they do not match, the admission ticket may have been transferred to a third party, and the process proceeds to step S67. On the other hand, if they match, there is no possibility of unauthorized entry, so admission is permitted and the visitor is guided into the arcade.

[0159] Next, in step S67, since it was determined in step S66 that the facial image at the time of the lottery and the facial image at the time of entry did not match, the unauthorized entry flag is set ON. Next, in step S68, it is determined whether or not the number of times the person has been registered as a fraudulent entry candidate is greater than a predetermined threshold value Th1. Here, if the number of times that a person has been registered as a fraudulent entry candidate is already greater than the threshold value Th1, the process proceeds to step S69, where a notice is sent to the manager, store staff of the amusement facility, etc. This allows the manager and store staff to take measures such as refusing entry to a person who has a history of being registered as a fraudulent entry candidate as a habitual fraudulent entry perpetrator, or warning the person to stop fraudulent entry.

[0160] On the other hand, if the number of times is equal to or less than the predetermined threshold Th1, the manager and store staff are not notified, entry is permitted, and the process returns to step S51 to determine the next entrant. In the process at the time of entry, the above-mentioned processes from step S51 to step S69 are repeated until there are no more visitors holding entry turn tickets.

[0161] <Matching process with registered fraudulent entry candidates> In the entrance management device 10 of this embodiment, the process of comparing facial images of registered candidates for unauthorized entry with facial images acquired at each stage (before the lottery, at the lottery, and at the time of entry) performed in step S19 before the lottery (FIG. 15), in step S40 at the time of the lottery (FIG. 16), and in step S60 at the time of entry (FIG. 17) is performed according to the flowchart shown in FIG. 18.

[0162] The previously registered fraudulent entry candidates that are compared here may be data accumulated at one of the amusement facilities, or data regarding fraudulent entry candidates accumulated at multiple amusement facilities may be shared between the multiple amusement facilities. This allows information about suspected fraudulent entry to be shared among multiple gaming arcades in a particular area or among multiple affiliated arcades, making it possible to appropriately identify and deal with fraudulent activities by suspected fraudulent entry.

[0163] 18, in step S71, it is determined whether matching has been completed for the number of unauthorized entry candidates previously registered. That is, in step S71, the process is repeated until matching has been completed between face images taken before the lottery, at the lottery, and at the time of entry and face images of all unauthorized entry candidates previously registered. Therefore, in step S71, when matching is completed for the number of previously registered unauthorized entry candidates, the process ends, and if not completed, the process proceeds to step S72.

[0164] Next, in step S72, face images of previously registered fraudulent entry candidates are retrieved one by one from the dictionary data 16a in the storage unit 16 and checked. Next, in step S73, it is determined whether the degree of similarity between the facial images of previously registered fraudulent entry candidates stored in dictionary data 16a and the facial images taken before the lottery, at the time of the lottery, and at the time of entry is greater than a predetermined threshold value Th2, i.e., whether they are similar.

[0165] If the difference is greater than the predetermined threshold Th2, that is, if the two facial images are similar, the process proceeds to step S74. On the other hand, if the difference is equal to or less than the predetermined threshold Th2, that is, if the two facial images are not similar, the process returns to S71 to perform matching with the next dictionary data. Next, in step S74, since it was determined in step S73 that the person resembles a fraudulent entry candidate previously registered, it is determined that the person is the same person, and the fraudulent entry candidate flag is set to ON.

[0166] Next, in step S75, the number of fraudulent acts of this fraudulent entry candidate is updated by +1. Next, in step S76, if the unauthorized entry suspect has been notified, the notification history is updated, and the process returns to step S71. In the process of matching against previously registered candidates for unauthorized entry, the above steps S71 to S76 are repeated until the process of matching the facial images taken before the lottery, at the time of the lottery, and at the time of entry with the facial images of all previously registered candidates for unauthorized entry is completed.

[0167] <Facial image matching process with photographs taken before and during the lottery> In the entrance management device 10 of this embodiment, the process of matching the face image acquired before the lottery, which is carried out in step S45 at the time of the lottery (FIG. 16), is carried out according to the flowchart shown in FIG. That is, as shown in FIG. 19, in step S81, the barcode attached to the lottery participation ticket distributed before the lottery is read by the barcode reader 40, and a face image linked to the lottery participation number is read from the dictionary data 16a in the memory unit 16.

[0168] Next, in step S82, the face image of the spectator taken by the camera 21 at the time of the lottery is collated with the face image before the lottery that was read out from the memory unit 16. Next, in step S83, it is determined whether the similarity between the two face images compared is smaller than a predetermined threshold Th3. If it is determined that the similarity between the face images is smaller than the threshold Th3, it is determined that there is a high possibility that the face images are different people, and the process proceeds to step S84. On the other hand, if the similarity between the face images is equal to or greater than the threshold Th3, it is determined that there is a high possibility that the person before and at the time of the lottery is the same person, and the person is not a candidate for unauthorized entry, and the process ends.

[0169] Next, in step S84, since it has been determined in step S83 that the similarity of the face image is smaller than the threshold value Th3, that is, that there is a possibility that the person is a fraudulent entry candidate, the fraudulent entry candidate flag is turned ON. Next, in step S85, the two people whose face images before and at the time of the lottery, which have been determined in step S83 to possibly be different people, are registered in the dictionary data 16a of the storage unit 16 as candidates for fraudulent entry.

[0170] In this case, the person in the face image before the lottery is registered in the dictionary data 16a as the giver who gave the lottery participation ticket to a third party, and the person in the face image at the time of the lottery is registered as the giver who received the lottery participation ticket from the third party. Next, in step S86, the number of fraudulent acts=1 is registered for the two persons whose face images are registered in the dictionary data 16a as fraudulent entry candidates before and at the time of the lottery. Next, in step S87, the notification history to the administrator or the like is updated for the two people whose face images are registered in the dictionary data 16a before and at the time of the lottery as fraudulent entry candidates, and the process ends.

[0171] <Facial image matching process with photos taken at the time of lottery and entry> In the entrance management device 10 of this embodiment, the process of matching with the face image acquired at the time of the lottery performed in step S65 at the time of entrance (FIG. 17) is performed according to the flowchart shown in FIG.

[0172] That is, as shown in FIG. 20, in step S91, the barcode attached to the admission order ticket distributed at the time of the lottery is read by the barcode reader 40, and a facial image linked to the admission order is read from the dictionary data 16a in the memory unit 16. Next, in step S92, the face image of the visitor taken by camera 21 at the time of entrance is collated with the face image read from memory unit 16 at the time of the lottery.

[0173] Next, in step S93, it is determined whether the similarity between the two face images compared is smaller than a predetermined threshold Th4. If it is determined that the similarity between the face images is smaller than the threshold Th4, it is determined that the face images are likely to be different people, and the process proceeds to step S94. On the other hand, if the similarity between the face images is equal to or greater than the threshold Th4, it is determined that the person at the time of the lottery and the person at the time of entry are likely to be the same person, and the person is not a candidate for unauthorized entry, and the process ends.

[0174] Next, in step S94, since it has been determined in step S93 that the similarity of the face image is smaller than the threshold value Th4, that is, that there is a possibility that the person is a fraudulent entry candidate, the fraudulent entry candidate flag is turned ON. Next, in step S95, the two people whose face images were determined in step S93 to possibly be different people at the time of the lottery and at the time of entry are registered in the dictionary data 16a of the storage unit 16 as candidates for fraudulent entry.

[0175] In this case, the person whose face image is captured at the time of the lottery is registered in dictionary data 16a as the transferor who transferred the admission number ticket to a third party, and the person whose face image is captured at the time of admission is registered as the transferee who received the admission number ticket from the third party. Next, in step S96, the number of fraudulent acts=1 is registered for the two persons whose face images were registered in the dictionary data 16a as fraudulent entry candidates at the time of the lottery and at the time of entry. Next, in step S97, the notification history to the administrator or the like is updated for the two people whose facial images were registered in the dictionary data 16a as fraudulent entry candidates at the time of the lottery and at the time of entry, and the process ends.

[0176] <Face quality evaluation process> In the entrance management device 10 of this embodiment, the face quality evaluation processing performed in step S16 before the lottery (FIG. 15), step S37 during the lottery (FIG. 16), and step S57 during entrance (FIG. 17) is performed according to the flowchart shown in FIG. 21(a).

[0177] That is, as shown in Fig. 21(a), in step S101, it is determined whether or not the left-right angle (Yaw angle) indicating the orientation of the face included in the face image (see Fig. 21(b)) is smaller than a predetermined threshold Th5. Here, if the Yaw angle is smaller than the threshold Th5, the left-right orientation of the face is determined to be OK, and the process proceeds to step S102. On the other hand, if the Yaw angle is equal to or larger than the threshold Th5, the left-right orientation of the face is determined to be NG, and the process proceeds to step S106.

[0178] Next, in step S102, it is determined whether the pitch angle (see FIG. 21(b)) indicating the orientation of the face included in the face image is smaller than a predetermined threshold Th6. If the pitch angle is smaller than threshold Th6, the up-down orientation of the face is determined to be OK, and the process proceeds to step S103. On the other hand, if the pitch angle is equal to or greater than threshold Th6, the up-down orientation of the face is determined to be NG, and the process proceeds to step S106.

[0179] Next, in step S103, it is determined whether or not the rotation angle (Roll angle) indicating the inclination of the face included in the face image (see FIG. 21(b)) is smaller than a predetermined threshold Th7. Here, if the Roll angle is smaller than the threshold Th7, the inclination of the face is determined to be OK, and the process proceeds to step S104. On the other hand, if the Roll angle is equal to or larger than the threshold Th7, the inclination of the face is determined to be NG, and the process proceeds to step S106.

[0180] Next, in step S104, for the face image whose face orientation (left / right, up / down, inclination) is determined to be OK, it is determined whether the eyes are closed. If it is determined that the eyes are not closed, the process proceeds to step S105. On the other hand, if it is determined that the eyes are blinking, the process proceeds to step S106. In addition to determining whether the eyes are closed in step S104, it may also be determined whether any part of the facial features is hidden, for example, when the mouth is intentionally hidden with a mask or the eyes are hidden with sunglasses.

[0181] Next, in step S105, since all the determinations in steps S101 to S104 have been cleared, the quality is determined to be OK, and the process ends. Next, in step S106, since any one of the determinations in steps S101 to S104 is determined to be NG, the quality is determined to be NG, a ticket issuance disabled signal is transmitted from the entrance management device 10 to the ticket issuing machine 30, and the process is terminated.

[0182] Here, if the quality of the face image used for face matching does not meet the matching criteria in face matching unit 15, there is a possibility that the person may be intentionally taking measures such as turning their face away in order to replace the person with another person. For this reason, for a person who refuses to have a proper face image taken, processing can be performed so that a lottery participation ticket cannot be issued even if the ticket issue button 31 is pressed in step S24, or an admission order ticket cannot be issued even if the ticket issue button 31 is pressed in step S47.

[0183] <List display and printing process> In the admission management system 1 of this embodiment, the face images, dictionary data, and notification history data stored in the memory unit 16 of the admission management device 10 are processed according to the flowchart shown in Figure 22 so that the face images, dictionary data, and notification history data stored in the memory unit 16 of the admission management device 10 can be managed by the amusement facility manager, store staff, etc. 22, in step S111, a function is selected to display / print a list of data required by the administrator, etc. The functions selected here include displaying / printing a list including face images registered as unauthorized entry candidates, displaying / printing a list including face images registered as dictionary data, and displaying / printing a list of notification history.

[0184] If the administrator or the like selects to display / print a list of face images in step S111, a list (see FIG. 11) including data on the face images, lottery participation numbers, and entry order stored in the memory unit 16 is read out in step S112. Next, in step S113, a list including the lottery participation number, pre-lottery face image, admission order, lottery face image, and admission face image shown in Fig. 11 is displayed on the display unit 10a of the admission management device 10. Furthermore, the list is printed out from the printer 50 as necessary.

[0185] If the administrator or the like selects to display / print a list of the dictionary data 16a in step S111, a list of the dictionary data 16a stored in the storage unit 16 (see FIG. 9) is read out in step S114. Next, in step S115, a list of dictionary data including the dictionary number, face image registered as a fraudulent entry candidate, registration date and time, type of fraudulent act, number of times of notification, and comment shown in Fig. 9 is displayed on the display unit 10a of the entrance management device 10. Furthermore, the list is printed out from the printer 50 as necessary.

[0186] If the administrator or the like selects to display / print a list of the notification history in step S111, the list of the notification history stored in the storage unit 16 (see FIG. 10) is read out in step S116. Next, in step S117, a list including the face images of visitors with notification history, notification dictionary numbers, types of misconduct, and notification dates and times, as shown in Fig. 10, is displayed on the display unit 10a of the entrance management device 10. Furthermore, the list is printed out from the printer 50 as necessary.

[0187] <Matching process between face images before and after entry> In the entrance management system 1 of this embodiment, first, according to the flowcharts shown in Figures 23 to 26, an entrance management method is implemented in which a facial image taken before entering an amusement facility is compared with a facial image taken within the amusement facility after entry, and suspected unauthorized entry is detected and registered. That is, as shown in FIG. 23, the entrance management system 1 mainly performs face recognition processing S201 at the time of entrance, face recognition S202 using face images captured by cameras 102-104 installed on each gaming machine 100, and dictionary sharing processing S203 of dictionary data of registered fraudulent entry candidates as the overall flow after entry to an amusement facility.

[0188] The steps S201 to S203 will be described in detail below. <Detection process of registered fraudulent entry candidates after their entry> In the entrance management device 10 of this embodiment, the process of detecting repeat unauthorized entry suspects after entry is performed according to the flowchart shown in FIG. 24 by comparing face images of previously registered unauthorized entry suspects with face images taken after entry.

[0189] In the flow shown in FIG. 24, a face recognition process will be described using a face image captured of a player who sits in front of each gaming machine 100 after entering the gaming facility. The cameras for capturing face images are not limited to the cameras 102-104 installed near each gaming machine 100, but may be other cameras 60a-60c, 61a-61c, 62a-62d installed within the gaming facility.

[0190] That is, in step S211, it is determined whether or not to continue the process until the process of all the players who have entered the gaming facility and sat in front of a specific gaming machine 100 with a high setting, for example, has been completed. At this time, the target person whose face image is captured by the cameras 102-104 installed near the gaming machine 100 may be, for example, a spectator identified by the person identification unit 12 using images captured by the multiple cameras 60-62 installed in the gaming facility after the spectator enters. In this way, by tracking a spectator who has been targeted at the time of entry and acquiring a face image, it is possible to appropriately determine whether or not the spectator is a candidate for unauthorized entry.

[0191] Furthermore, the photographing of the face image by the cameras 102, 103 installed near the gaming machine 100 may be triggered, for example, by the detection of a gaming medium in the out ball counter 105 by operating the gaming machine 100. In addition, the photographing of the face image may be triggered by the operation of an operating tool of the gaming machine 100, the detection of a gaming medium in the in ball counter, or the detection of a person sitting in a seat of the gaming machine 100 using a human sensor or the like.

[0192] Furthermore, the capture of a facial image by the camera 104 installed on the inter-machine 110 may be triggered by the deposit detection unit 106 detecting that a visitor has inserted money, a prepaid card, or the like into the inter-machine 110. By capturing face images at the above-mentioned timing, the face image of the visitor can be captured from substantially the front, improving the accuracy of face authentication.

[0193] Next, in step S212, for example, the cameras 102-104 are used to capture facial images of players seated in front of each gaming machine 100. The captured facial images are then immediately transmitted from the cameras 102-104 to the admission management device 10, and are received by the image acquisition unit 11 of the admission management device 10. Next, in step S213, the face detection unit 13 of the entrance management device 10 detects a part that resembles a face included in the face image acquired by the image acquisition unit 11.

[0194] Next, in step S214, it is determined whether or not a part resembling a face has been detected by face detection unit 13. If a part resembling a face has been detected, the process proceeds to step S214. On the other hand, if a part resembling a face has not been detected, the process returns to step S212, and the face image is captured again using cameras 102-104, for example. Next, in step S215, the face direction and organ detection unit 14a of the entrance management device 10 detects the face direction and facial organs from the face-like parts.

[0195] Next, in step S216, the face quality evaluation unit 14b of the entrance management device 10 judges whether the face image is of a quality that can withstand the judgment unit 17 as to whether it is the same person or not, depending on the face direction and the presence or absence of organs detected by the face direction and organ detection unit 14a. Next, in step S217, it is determined whether the facial quality evaluation unit 14b evaluates the facial quality as OK or not. If the facial quality is OK, the process proceeds to step S218. On the other hand, if the facial quality is NG, the process returns to step S212, and the facial image is captured again using the cameras 102 to 104, for example.

[0196] Next, in step S218, the face image whose face quality has been determined to be OK is stored in the face image database of the storage unit 16. Next, in step S219, the face matching unit 15 compares the face images of previously registered suspected fraudulent entry persons stored as dictionary data 16a in the memory unit 16 with the face images of entrants photographed in front of each gaming machine 100.

[0197] Next, in step S220, the facial image comparison in step S219 is performed to determine whether or not there is a match, that is, the facial image of the previously registered fraudulent entry candidate is compared with the facial image of the entrant photographed in front of the gaming machine 100 after entering the gaming facility to determine whether or not the two are the same person. If it is determined that there is a match, the process proceeds to step S221, and if it is determined that there is no match, it is determined that there is no problem, and the process returns to step S211 to proceed to the facial authentication process for the next entrant.

[0198] Next, in step S221, since the determination in step S220 indicates that the face image of the illegal entry candidate registered in the past matches the face image of the entrant photographed after entry, the illegal entry perpetrator flag is turned ON. Next, in step S222, it is determined whether the number of times the person has been registered as a fraudulent entry candidate is greater than a predetermined threshold value Th1.

[0199] Here, if the number of times the person has been registered as a fraudulent entry candidate is already greater than the threshold value Th1, the process proceeds to step S223, where a notice is sent to the manager of the amusement facility, store staff, etc. This allows the manager and store staff, etc. to take measures such as urging the person who has been registered as a fraudulent entry candidate to leave the facility as a habitual fraudulent entry offender, or warning them.

[0200] On the other hand, if the number of times is below the predetermined threshold Th1, no notification is given to the manager or store staff, etc., the flag indicating a possible fraudulent entry is simply turned ON, the process ends, and the process returns to step S211 to perform face recognition processing for the next entrant. In the face authentication process after entry, as described above, the processes from step S211 to step S223 are repeatedly performed on all entrants seated in, for example, a gaming machine 100 with a high setting.

[0201] <Detection of replacement after entry> Furthermore, the admission management device 10 of this embodiment performs a process according to the flowchart shown in FIG. 25 to detect unauthorized entrants who, despite having entered legitimately through a lottery or the like, give up a seat in a gaming machine 100 with a high setting that they secured after entering to a third party who enters later, so-called substitution.

[0202] That is, in step S311, it is determined whether or not to continue the process until the process of all the players who have entered the gaming facility and sat in front of a specific gaming machine 100 with a high setting, for example, has been completed. Next, in step S312, for example, the cameras 102-104 are used to capture facial images of players seated in front of each gaming machine 100. The captured facial images are then immediately transmitted from the cameras 102-104 to the entrance management device 10, and are received by the image acquisition unit 11 of the entrance management device 10.

[0203] Next, in step S313, the face detection unit 13 of the entrance management device 10 detects a part that resembles a face included in the face image acquired by the image acquisition unit 11. Next, in step S314, it is determined whether or not a part resembling a face has been detected by the face detection unit 13. If a part resembling a face is detected, the process proceeds to step S314. On the other hand, if a part resembling a face is not detected, the process returns to step S312, and the face image is captured again, for example, using the cameras 102-104 installed near the gaming machine 100 with a high setting.

[0204] Next, in step S315, the face direction and organ detection unit 14a of the entrance management device 10 detects the face direction and facial organs from the face-like parts. Next, in step S316, the face quality evaluation unit 14b of the entrance management device 10 judges whether the face image is of a quality that can withstand the judgment unit 17 as to whether it is the same person or not, depending on the face direction and the presence or absence of organs detected by the face direction and organ detection unit 14a.

[0205] Next, in step S317, it is determined whether the facial quality evaluation unit 14b evaluates the facial quality as OK. If the facial quality is OK, the process proceeds to step S318. On the other hand, if the facial quality is NG, the process returns to step S312, and the facial image is re-captured using the cameras 102-104 installed near the gaming machine 100 with a high setting, for example. Next, in step S318, the face image whose face quality has been determined to be OK is stored in the face image database of the storage unit 16.

[0206] Next, in step S319, the process waits until a predetermined time has elapsed since the face image of a player seated in front of a specific gaming machine 100 was first acquired. The predetermined time period can be freely set by an administrator or the like within a range of, for example, 5 to 30 minutes. Next, in step S320, after a predetermined time has elapsed in step S319, a face image of a player seated at the same gaming machine 100 is photographed again.

[0207] Next, in step S321, the face detection unit 13 of the entrance management device 10 detects a part that resembles a face included in the face image acquired by the image acquisition unit 11. Next, in step S322, it is determined whether or not a part resembling a face has been detected by the face detection unit 13. If a part resembling a face has been detected, the process proceeds to step S323. On the other hand, if a part resembling a face has not been detected, the process returns to step S320, and the face image is captured again using the cameras 102-104 installed in the vicinity of the same gaming machine 100.

[0208] Next, in step S323, the face direction and organ detection unit 14a of the entrance management device 10 detects the face direction and the facial organs from the face-like parts. Next, in step S324, the face quality evaluation unit 14b of the entrance management device 10 judges whether the face image is of a quality that can withstand the judgment unit 17 as to whether it is the same person or not, depending on the face direction and the presence or absence of organs detected by the face direction and organ detection unit 14a.

[0209] Next, in step S325, it is determined whether the facial quality evaluation unit 14b evaluates the facial quality as OK or not. If the facial quality is OK, the process proceeds to step S326. On the other hand, if the facial quality is NG, the process returns to step S320, and the facial image is captured again using the cameras 102 to 104 installed near the same gaming machine 100. Next, in step S326, the face image whose face quality has been determined to be OK is stored in the face image database of the storage unit 16.

[0210] Next, in step S327, a facial image of a player seated at the same gaming machine 100 taken before a predetermined time has elapsed (e.g., immediately after entering) is compared with a facial image taken after the predetermined time has elapsed (e.g., 15 minutes). Next, in step S328, the facial image comparison in step S327 is performed to determine whether or not there is a match, that is, the two facial images taken before and after a predetermined time has elapsed are compared to determine whether or not they are the same person. If it is determined that there is a match, it is determined that there is no problem, and the process returns to step S311 to proceed to the facial authentication process for the next visitor, but if it is determined that there is no match, it is determined that there is a possibility that the visitor has been replaced by a visitor who entered later, and the process proceeds to step S329.

[0211] The facial image determined here before the specified time has elapsed is a facial image of a person who has properly entered through a lottery or the like, and is a facial image that matches a facial image taken of the person who properly entered before entering. Next, in step S329, since it is determined in step S328 that the person before and after the lapse of the predetermined time has been replaced by a different person, the unauthorized entry flag is turned ON for the person in the face images before and after that.

[0212] Next, in step S330, it is determined whether the number of times the person has been registered as a fraudulent entry candidate is greater than a predetermined threshold value Th1. Here, if the number of times the person has been registered as a fraudulent entry candidate is already greater than the threshold value Th1, the process proceeds to step S331, where a notice is sent to the manager of the gaming facility, store staff, etc. This allows the manager and store staff, etc. to take measures such as urging the person who has a history of being registered as a fraudulent entry candidate in the past and who entered late to take over a gaming machine 100 with a high setting to leave as a habitual fraudulent entry offender or giving him a warning.

[0213] On the other hand, if the number of times is below the predetermined threshold Th1, no notification is given to the manager or store staff, etc., the flag indicating a possible fraudulent entry is simply turned ON, the process ends, and the flow returns to step S311 to perform face recognition processing for the next entrant. In the face authentication process after entry, as described above, the processes from step S311 to step S331 are repeatedly performed on all entrants seated in, for example, the gaming machines 100 with high settings.

[0214] <Dictionary data update process> In the entrance management device (first entrance management device) 10 of this embodiment, in order to share the dictionary data stored in the memory unit 16 by the above-mentioned processing with, for example, another entrance management device (second entrance management device) installed in one amusement facility, or with other entrance management devices (second entrance management devices) installed in multiple amusement facilities, a dictionary sharing process is performed according to the flowcharts shown in Figures 26 and 27.

[0215] That is, as shown in FIG. 26, in step S341, the dictionary data 16a stored in the storage unit 16 is referenced to check whether or not any dictionary data has been added. Next, in step S342, it is determined whether or not dictionary data has been added. If it is determined that data has been added, the process proceeds to step S343, and if it is determined that data has not been added, the process ends. Next, in step S343, since it is determined in step S342 that dictionary data has been added, the added dictionary data is transmitted, for example, to another admission management device 10 or to an admission management device 10 in another game center.

[0216] Next, in step S344, the added dictionary data is stored in the storage unit 16. Next, in step S345, it is determined whether or not all of the added dictionary data has been saved in storage unit 16. If it is determined that all of the added dictionary data has been saved, the process ends, and if it is determined that there is still unsaved dictionary data, the process returns to step S344. Then, in another entrance management device (second entrance management device) that receives the added dictionary data from the entrance management device (first entrance management device) 10 that has executed the flow shown in FIG. 26, the dictionary sharing process is performed according to the flowchart shown in FIG. 27.

[0217] That is, in step S351, the number of added dictionary data items is received. Next, in step S352, it is determined whether or not dictionary data has been added. If it is determined that some dictionary data has been added, the process proceeds to step S352, and if it is determined that no dictionary data has been added, the process ends. Next, in step S353, the added dictionary data is received from the entrance management device (first entrance management device) 10.

[0218] Next, in step S354, the received added dictionary data is stored in the storage unit 16. Next, in step S355, it is determined whether or not all of the added dictionary data has been received. If it is determined that all of the dictionary data has been received, the process proceeds to step S356, but if it is determined that there is still unreceived dictionary data, the process returns to step S354. Next, in step S356, all the added dictionary data is stored in the storage unit 16, and data on the fraudulent entry candidates is registered.

[0219] <Main features> The entrance management device 10 of this embodiment is a device for managing visitors after they enter an amusement facility, and includes an image acquisition unit 11, a face detection unit 13, a face matching unit 15, a judgment unit 17, and a registration unit 18. The image acquisition unit 11 acquires a first image including a face of a first person photographed by a camera 21 or the like before entering the amusement facility, and acquires a second image including a face of a second person photographed by cameras 60-62, 102-104 in the amusement facility after entering the amusement facility. The face detection unit 13 detects the facial parts of the first person and the second person included in the first image and the second image. The face matching unit 15 compares the faces of the first person and the second person included in the first image and the second image detected by the face detection unit 13. The judgment unit 17 judges whether the first person and the second person included in the first image and the second image are the same person based on the comparison result in the face matching unit 15. When it is determined as a result of the determination in the determination unit 17 that the first person and the second person included in the first image and the second image are different people, the registration unit 18 registers the first person and the second person as candidates for unauthorized entry.

[0220] This allows a first image taken before entering an amusement facility (when the numbered ticket is distributed, when the lottery is drawn, or when entering) to be compared with a second image taken inside the amusement facility after entry to detect whether the person has been replaced by a different person, and by registering the people before and after the replacement (the first person and the second person) as candidates for fraudulent entry, it becomes possible to manage people who may be fraudulent entrants. As a result, it is possible to properly grasp and manage the habitual nature of a person who may have committed a fraudulent act, such as giving up a seat on a gaming machine 100 reserved by a first person to a second person, who is a third party, after entering an amusement facility.

[0221] The entrance management device 10 of this embodiment is a device for managing visitors after they enter an amusement facility, and includes an image acquisition unit 11, a face detection unit 13, a face matching unit 15, a determination unit 17, and a registration unit 18. The image acquisition unit 11 acquires a first image including a face of a first person who was previously registered as a fraudulent entry candidate, and acquires a second image including a face of a second person photographed by cameras 60-62, 102-104 in the amusement facility after the visitor enters the amusement facility. The face detection unit 13 detects the facial parts of the first person and the second person included in the first image and the second image. The face matching unit 15 compares the faces of the first person and the second person included in the first image and the second image detected by the face detection unit 13. The determination unit 17 determines whether the first person and the second person included in the first image and the second image are the same person based on the comparison result in the face matching unit 15. When it is determined as a result of the determination in the determination unit 17 that the first person and the second person included in the first image and the second image are the same person, the registration unit 18 registers the second person as a fraudulent entry candidate.

[0222] This allows a first image including the face of a first person previously registered as a fraudulent entry candidate to be compared with a second image including the face of a person who has entered the amusement facility, and if a person identical to a person previously registered as a fraudulent entry candidate is detected among those who have entered the amusement facility, that person can be registered again as a fraudulent entry candidate, thereby making it possible to manage people who may be frequent fraudulent entrants. As a result, after entering an amusement facility, the habitual nature of a person who may be a regular unauthorized entrant can be properly understood and managed.

[0223] [Other embodiments] Although one embodiment of the present invention has been described above, the present invention is not limited to the above embodiment, and various modifications are possible without departing from the gist of the invention.

[0224] (A) In the above embodiment, an example has been described in which the present invention is realized as the entrance management device 10 and the entrance management system 1 including the entrance management device 10. However, the present invention is not limited to this. For example, the present invention may be realized as an entrance management program that causes a computer to execute the entrance management methods shown in the flowcharts of FIGS.

[0225] This entrance management program is stored in a memory (storage unit) mounted on the entrance management device, and the CPU reads the entrance management program stored in the memory and causes the hardware to execute each step. More specifically, the CPU reads the entrance management program and forms each component such as the image acquisition unit, face detection unit, face matching unit, judgment unit, and registration unit described above, thereby achieving the same effects as those described above. The present invention may also be realized as a recording medium storing an admission management program.

[0226] (B) In the above embodiment, the information on the face image before entry, which is compared with the face image after entry, is explained by taking an example in which face images taken by the camera 21 when the lottery participation ticket is distributed before entry to the game arcade, when the lottery is drawn, and when the player enters the game arcade. However, the present invention is not limited to this. For example, information previously registered as a suspected unauthorized entry may be used as information before entry and compared with a face image photographed after entry.

[0227] (C) In the above embodiment, an example has been described in which a PC used by an administrator is used as the entrance management device 10. However, the present invention is not limited to this. For example, the tablet terminal shown in FIG. 1 may be used as the entrance management device. In this case, the tablet terminal can function as an entrance management device by receiving facial images taken by multiple cameras installed within the amusement park and comparing them with images taken before entry.

[0228] (D) In the above embodiment, an example was given in which face images were acquired in three stages (before the lottery, at the time of the lottery, and at the time of entry) before entering an amusement facility, and detected candidates for unauthorized entry were registered. However, the present invention is not limited to this.

[0229] For example, before entering an amusement facility, face images may be acquired in two stages to determine whether or not the person is a candidate for unauthorized entry. Specifically, in the case where numbered tickets are distributed before entry and people are allowed to enter in the order of the numbered ticket, the facial images taken at the time of the ticket distribution and at the time of entry may be compared to determine whether or not the person is a candidate for unauthorized entry. In other words, the present invention can also be applied to entry management without a lottery.

[0230] In addition, in cases where lottery participation tickets are not distributed before the lottery and people are admitted in the order of admission determined by the lottery, facial images taken at the time of the lottery and at the time of admission may be compared to determine whether or not a person is a candidate for fraudulent admission. Incidentally, before entering an amusement facility, a face image may be acquired at four or more stages to determine whether or not the person is a candidate for unauthorized entry.

[0231] (E) In the above embodiment, an example was described in which the entrance management device 10, which acquires a face image of a visitor before entering and judges whether the visitor is a candidate for unauthorized entry, acquires a face image of the visitor photographed inside the amusement facility after entering and judges whether the visitor is a candidate for unauthorized entry. However, the present invention is not limited to this. For example, a first entrance management device that acquires facial images of entrants before entry and determines whether they are suspected of unauthorized entry, and a second entrance management device that acquires facial images of entrants after entry and determines whether they are suspected of unauthorized entry may be provided as separate devices.

[0232] (F) In the above embodiment, an example was given in which a camera 102 installed on the machine indicator lamp 101 on the top of the gaming machine 100, a camera 103 installed inside the gaming machine 100, and a camera 104 installed on the inter-machine machine 110 were used to capture facial images of patrons seated on the gaming machine 100. However, the present invention is not limited to this. For example, any one or two of the cameras 102 to 104 may be used as a camera for capturing facial images of players seated at game machines.

[0233] (G) In the above embodiment, an example has been described in which the barcodes attached to the lottery participation tickets (numbered tickets) distributed before entry and the entry order tickets given at the time of the lottery are read by the barcode reader 40 to read out face images taken before and at the time of the lottery, and compared with the face image taken at the time of entry. However, the present invention is not limited to this. For example, instead of bar codes, lottery participation tickets (numbered tickets) and admission order tickets with identification codes such as numbers and symbols may be given, and a device for reading them may be used.

[0234] (H) In the above embodiment, an example was described in which the face direction detection unit and the face organ detection unit detect the face direction and the face organs, respectively, when determining whether or not the face images are of the same person. However, the present invention is not limited to this. For example, in order to determine whether or not the images are of the same person, a comparison method other than the comparison based on the face orientation and the detection results of the facial features may be used.

[0235] (I) In the above embodiment, an example was described in which the storage unit 16 for storing face images and the like was provided inside the entrance management device 10. However, the present invention is not limited to this. For example, the facial image captured by the camera may be stored in a server device, cloud space, etc. located outside the entrance management device, and the image acquisition unit may acquire the facial image from the server device or cloud space.

[0236] (J) In the above embodiment, an example has been described in which the entrance management device 10, the tablet terminal 20 (camera 21), the ticket issuing machine 30, the gaming machine 100 installed in the gaming facility, the inter-machine machine 110, and the multiple cameras 60-62, 102-104 are connected to each other via a wireless communication line 2 such as a wireless LAN. However, the present invention is not limited to this. For example, other wireless communication means such as Bluetooth (registered trademark) may be used as the wireless communication line instead of wireless LAN such as Wi-Fi (registered trademark). Alternatively, the entrance management device, the imaging device, and the ticket issuing machine may be connected to each other via wired communication.

[0237] (K) In the above embodiment, an example was given in which, when the number of times a person is registered as a fraudulent entry candidate exceeds a predetermined threshold, a notification is given to a facility manager or store staff, etc., that a fraudulent entrant has entered the facility. However, the present invention is not limited to this. For example, when a person is registered as a potential unauthorized entrant, a notification may be immediately sent to a facility manager or the like that a person who has entered the facility unauthorizedly has entered the facility. That is, the threshold for notifying an administrator or the like of a suspected unauthorized entry may be set to "0."

[0238] (L) In the above embodiment, an example was given in which the face quality evaluation unit 14b uses the face direction and face organs detected by the face direction and organ detection unit 14a to determine whether the face parts included in the face images captured by the camera 21 and the multiple cameras 60-62, 102-104 installed in the game center have the quality required to determine whether they are of the same person. However, the present invention is not limited to this.

[0239] For example, the quality of a face image may be evaluated by determining whether all the facial features are present in the face image. In other words, in the present invention, it is not essential to use both the face orientation and the facial features as conditions for determining face quality, and face quality may be evaluated using only one of them.

[0240] (M) In the above embodiment, an example has been described in which the face direction and organ detection unit 14a detects the face direction and organs included in the face image, but the present invention is not limited to this. For example, a face direction detection section that detects the direction of a face and a face organ detection section that detects face organs may be configured separately. [Industrial Applicability]

[0241] The entrance management device of the present invention has the effect of being able to properly grasp and manage any fraudulent behavior by visitors after entering an amusement facility, and therefore can be widely applied to devices and systems that manage visitors to various facilities, etc. [Explanation of symbols]

[0242] 1. Admission Control System 2. Wireless communication lines 10 Entrance control device 10a Display section 11 Image acquisition section 12 Person identification part 13 Face detection section 14a Facial orientation organ detection unit 14b Face quality evaluation section 15 Face matching unit 16 Memory section 16a Dictionary Data 17 Judgment section 18 Registration Department 19. Notification Department 20 Tablet devices 21 Camera (first imaging device) 30 Ticket Machine 31 Ticket issue button 32 Receipts 40 Barcode Reader 50 Printers 60, 60a to 60c Camera (second imaging device) 61, 61a to 61c Camera (second imaging device) 62, 62a to 62d Camera (second imaging device) 100, 100a~100c Gaming machines 101, 101a~101c indicator lamp 102-104 Camera (second imaging device) 105 Out Ball Counter 106 Deposit detection unit 110,110a,110b Machine between machines 120a~120c entrance / exit 121a~121d Island equipment 122a Counting machine 122b Rental Machine 122c Vending machine P1 visitors

Claims

1. An admission management device for managing visitors after they enter an amusement facility, an image acquisition unit that acquires a first image including a face of a first person captured by a first imaging device before entry into the amusement facility, and acquires a second image including a face of a second person captured by a second imaging device in the amusement facility after entry into the amusement facility; a face detection unit that detects facial portions of the first person and the second person included in the first image and the second image; a face quality evaluation unit that determines whether or not the orientation of the faces of the first person and the second person detected by the face detection unit is within a predetermined angle range, or whether or not a condition of the presence or absence of facial features is satisfied; a face matching unit that compares the faces of the first person and the second person included in the first image and the second image that have been detected by the face detection unit and determined to be appropriate by the face quality evaluation unit; a determination unit that determines whether the first person and the second person included in the first image and the second image are the same person based on a result of the comparison in the face matching unit, and determines whether a lottery participation ticket or an admission order ticket can be issued in a ticket issuing machine; a registration unit that, when it is determined as a result of the determination by the determination unit that the first person and the second person included in the first image and the second image are different people, registers the first person and the second person as a candidate for unauthorized entry; An entrance management device comprising:

2. An admission management device for managing visitors after they enter an amusement facility, an image acquisition unit that acquires a first image including a face of a first person who has been registered in the past as a candidate for unauthorized entry, and acquires a second image including a face of a second person photographed by a second imaging device in the amusement facility after the second person has entered the amusement facility; a face detection unit that detects facial portions of the first person and the second person included in the first image and the second image; a face quality evaluation unit that determines whether or not the orientation of the faces of the first person and the second person detected by the face detection unit is within a predetermined angle range, or whether or not a condition of the presence or absence of facial features is satisfied; a face matching unit that compares the faces of the first person and the second person included in the first image and the second image that have been detected by the face detection unit and determined to be appropriate by the face quality evaluation unit; a determination unit that determines whether the first person and the second person included in the first image and the second image are the same person based on a result of the comparison in the face matching unit, and determines whether a lottery participation ticket or an admission order ticket can be issued in a ticket issuing machine; a registration unit that, when it is determined as a result of the determination by the determination unit that the first person and the second person included in the first image and the second image are the same person, registers the second person as a suspect of unauthorized entry; An entrance management device comprising:

3. a person identification unit that identifies a second person corresponding to a first person included in the first image by using a plurality of second images captured by a plurality of second imaging devices installed at a plurality of locations in the game center; In addition, 3. An entrance management device according to claim 1 or 2.

4. the image acquisition unit acquires the first image captured by the first imaging device when a numbered ticket for participating in a lottery for determining an entry order when entering the game facility is distributed, and / or when the lottery is held, and / or when entering the game facility; The entrance management device according to claim 1.

5. The image acquisition unit acquires the second image captured by the second imaging device installed in at least one of an entrance to the gaming facility, a gaming machine installed in the gaming facility, and an inter-machine machine installed between the gaming machines. The entrance management device according to any one of claims 1 to 4.

6. the image acquisition unit acquires a third image of a person seated in front of a first gaming machine when the gaming facility opens, and a fourth image of the person seated in front of the first gaming machine after a predetermined time has elapsed; The entrance management device according to any one of claims 1 to 5.

7. the determination unit determines the first person and the second person by using the fourth image as the second image. The entrance management device according to claim 6.

8. Further comprising a storage unit for storing the first image and the second image. An entrance management device according to any one of claims 1 to 7.

9. the storage unit stores dictionary data for matching with the first person and the second person who have been registered in the past as the unauthorized entry candidate; The entrance management device according to claim 8.

10. The image processing device further includes a face organ detection unit configured to detect predetermined face organs from face portions of the first person and the second person included in the first image and the second image. An entrance management device according to any one of claims 1 to 9.

11. The image processing device further includes a face direction detection unit that detects the face direction of the first person and the second person included in the first image and the second image. An entrance management device according to any one of claims 1 to 10.

12. A display unit that displays a list of the unauthorized entry candidates, In addition, An entrance management device according to any one of claims 1 to 11.

13. The system further includes a notification unit that notifies an administrator that a fraudulent entry candidate registered in the registration unit is an fraudulent entry candidate when the number of times the fraudulent entry candidate is determined to be such by the determination unit exceeds a predetermined threshold value. An entrance management device according to any one of claims 1 to 12.

14. A display unit that displays a list of the fraudulent entry candidates is further provided, making a list of the unauthorized entrants notified by the notification unit and displaying the list on the display unit; The entrance management device according to claim 13.

15. An entrance management device according to any one of claims 1 to 14; a first imaging device that captures the first image and a second imaging device that captures the second image; An admissions management system equipped with

16. The first imaging device and the second imaging device capture a still image or a video as the first image and the second image. The admission control system according to claim 15.

17. The entrance management device, the first imaging device, and the second imaging device transmit and receive various signals via wireless or wired communication. The entrance management system according to claim 15 or 16.

18. The entrance management device shares, among the plurality of game facilities, information regarding the fraudulent entry candidates determined using the first image and the second image acquired from the first imaging device and the second imaging device installed in each of the plurality of game facilities. An admission control system according to any one of claims 15 to 17.

19. An admission management program for managing visitors after they enter an amusement facility, a first image acquisition step of acquiring a first image including a face of a first person photographed by a first imaging device before the first person enters the game facility; a second image acquisition step of acquiring a second image including a face of a second person photographed by a second imaging device in the game facility after the person enters the game facility; a face detection step of detecting facial portions of the first person and the second person included in the first image and the second image; a face quality evaluation step of determining whether or not the orientation of the faces of the first person and the second person detected in the face detection step is within a predetermined angle range, or whether or not a condition of the presence or absence of facial features is satisfied; a face matching step of comparing the faces of the first person and the second person contained in the first image and the second image detected in the face detection step and determined to be appropriate in the face quality evaluation step; a determination step of determining whether or not the first person and the second person included in the first image and the second image are the same person based on a result of the comparison in the face matching step, and determining whether or not a lottery participation ticket or an admission order ticket can be issued in a ticket issuing machine; a registration step of registering the first person and the second person as a fraudulent entry candidate when it is determined that the first person and the second person included in the first image and the second image are different persons as a result of the determination in the determination step; An admission management program that causes a computer to execute an admission management method comprising the steps of:

20. An admission management program for managing visitors after they enter an amusement facility, A first image acquisition step of acquiring a first image including a face of a first person who has been registered in the past as a suspect of unauthorized entry; a second image acquisition step of acquiring a second image including a face of a second person photographed by a second imaging device in the game facility after the person enters the game facility; a face detection step of detecting facial portions of the first person and the second person included in the first image and the second image; a face quality evaluation step of determining whether or not the orientation of the faces of the first person and the second person detected in the face detection step is within a predetermined angle range, or whether or not a condition of the presence or absence of facial features is satisfied; a face matching step of comparing the faces of the first person and the second person contained in the first image and the second image detected in the face detection step and determined to be appropriate in the face quality evaluation step; a determination step of determining whether or not the first person and the second person included in the first image and the second image are the same person based on a result of the comparison in the face matching step, and determining whether or not a lottery participation ticket or an admission order ticket can be issued in a ticket issuing machine; a registration step of registering the second person as a suspect of unauthorized entry when it is determined in the determination step that the first person and the second person included in the first image and the second image are the same person; An admission management program that causes a computer to execute an admission management method comprising the steps of:

Images