Cheating detection system for a casino

Abstract

The present invention provides a new system for detecting cheating in games at a casino, or errors and cheating in the placement and accounting of chips. A cheating detection system for detecting cheating in a game in which chips are collected and paid out according to the result of the game, includes a camera (2) that photographs chips (9) received in a chip tray (17) of a dealer (5), an image analysis device (12) that analyzes an image photographed by the camera (2) to detect the amount of chips (9) received in the chip tray (17), a card distribution device (13) that determines the result of the game, and a control device (14) that compares the result of the game and the amount of chips (9) received in the chip tray (17) before and after the chips are collected and paid out to detect cheating.

Description

[0001] Divisional application

[0002] This application is a divisional application of patent application No. 201680045982.3, filed on August 2, 2016, with the title of "Cheating detection system for game house".

[0003] Reference of related applications

[0004] This application claims priority from Japanese Patent Application No. 2015-163213 filed on August 3, 2015, and Japanese Patent Application No. 2015-206735 filed on October 1, 2015, the contents of which are incorporated herein by reference. TECHNICAL FIELD

[0005] The present application relates to a system for detecting cheating in a game at a game house, or errors and cheating in placing and accounting for gaming chips. BACKGROUND

[0006] In a game house such as a casino, various cheating behaviors are being attempted to be prevented. The game house is provided with a monitoring camera for monitoring cheating behaviors, and based on images obtained by the monitoring camera, cheating in a game, and cheating in the recovery and payout of gaming chips different from the winning and losing results, and the like are determined, and cheating is prevented.

[0007] On the other hand, in order to grasp the number and total amount of gaming chips that have been placed, a scheme of attaching a wireless IC (RFID) tag to each gaming chip to grasp the amount of gaming chips has been proposed.

[0008] In the card game monitoring system described in International Publication No. 2015 / 107902, it is determined whether or not the gaming chips placed on the game table are recovered or paid out according to the winning and losing results by image analysis of changes in the gaming chips, and monitoring of cheating behaviors is performed. SUMMARY

[0009] PROBLEMS TO BE SOLVED BY THE INVENTION

[0010] An object of the present application is to provide a new system for detecting cheating in a game at a game house, or errors and cheating in placing and accounting for gaming chips.

[0011] SOLUTION TO PROBLEM

[0012] The cheating detection system of one embodiment of the present application is a cheating detection system in a casino having a plurality of gaming tables, and includes: a game recording device that records states of games played at the gaming tables as video by a camera; an image analysis device that performs image analysis on the recorded states of the games; a win / loss result determination device that determines win / loss results of the games played at the gaming tables; and a control device that detects cheating at the gaming tables using the image analysis results of the image analysis device and the win / loss results determined by the win / loss result determination device. The control device grasps the positions, types, and numbers of chips placed by players with the aid of the image analysis device, and grasps the total amount of chips in a chip tray of a dealer of the gaming table. The control device adds and subtracts the increase and decrease amounts of chips in the game calculated from the positions, types, and numbers of chips placed by all players in the game and the win / loss result of the game obtained by the win / loss result determination device to the total amount of chips in the chip tray before settlement of each game, and compares the expected total amount of chips in the chip tray after settlement at the end of the game with the actual total amount of chips in the chip tray at the end of the game obtained by the image analysis device, to determine whether there is a difference between the expected total amount and the actual total amount.

[0013] In the above-described cheating detection system, the control device can grasp the positions, types, and numbers of chips placed by players with the aid of the image analysis device, and grasp the actual total amount of chips in the chip tray at the end of the collection of all the losing chips placed by players. The control device can compare the expected total amount of chips in the chip tray obtained by adding the increase amount of the chip tray in the game to the expected total amount of chips in the chip tray calculated from the positions, types, and numbers of chips placed by losing players before settlement of each game, with the actual total amount of chips in the chip tray, to determine whether there is a difference between the expected total amount and the actual total amount.

[0014] In the above-described cheating detection system, the control device can compare the expected total amount of chips in the chip tray obtained by adding the increase amount of the chip tray in the game to the expected total amount of chips in the chip tray calculated from the positions, types, and numbers of chips placed by losing players before settlement of each game, with the actual total amount of chips in the chip tray, to determine that there is no difference between the expected total amount and the actual total amount, and compare the expected total amount of chips in the chip tray after settlement at the end of the game with the actual total amount of chips in the chip tray at the end of the game obtained by the image analysis device, to determine that there is a difference between the expected total amount and the actual total amount in the case where there is a difference between the expected total amount and the actual total amount, determine that there is a payout error, and generate a payout error signal that notifies of the payout error.

[0015] In the above-described fraud detection system, a game chip recovery tray that recovers and temporarily stores game chips placed by a losing player can be provided in the game chip tray. The image analysis device and the control device compare the expected total amount of game chips in the recovery game chip tray calculated from the position, type, and number of game chips placed by a losing player with the actual total amount of game chips in the recovery game chip tray, and determine whether there is a difference between the expected total amount and the actual total amount.

[0016] In the above-described fraud detection system, the actual total amount of game chips in the game chip tray after settlement at the end of a game can be obtained by the image analysis device at any one of the following times:

[0017] 1) when the payout of winning game chips is completed;

[0018] 2) when the cards used in the game are recovered and discarded in the discard area of the table;

[0019] 3) when a predetermined button attached to the win / loss determination device is pressed;

[0020] 4) when the sign indicating the win / loss is restored.

[0021] In the above-described fraud detection system, when the control device determines that the actual total amount of game chips grasped in the game chip tray of the dealer of the game table does not correspond to the increase / decrease amount of game chips calculated from the amounts of game chips placed by all players and the win / loss result of the game, the game record device can analyze the record of the game in which the difference occurred. The game record device is configured to assign an index or a time to the captured image, or can determine and reproduce the recovery or payout scene of game chips.

[0022] In the above-described fraud detection system, the image analysis device or the control device can be configured to obtain information on the type, number, and position of game chips placed even when a plurality of game chips placed on the game table are partially or entirely hidden due to the blind spot of the camera.

[0023] In the above-described fraud detection system, the control device can be configured to perform the following actions:

[0024] 1) grasps the position, type, and number of game chips placed at each play position of the game table, compares the win / loss history of each player obtained from the win / loss result of each game and the amount of game chips obtained with statistical data of past games, and extracts as an abnormal situation, or

[0025] 2) the state in which the amount of chips placed at the time of loss at the play position of the game table is less than the amount of chips placed at the time of win is compared with statistical data of past games, as an abnormality extraction.

[0026] In the above-described fraud detection system, the control device can compare the amount of chips grasped in the chip tray of the dealer of the game table with the amount of chips paid out in correspondence with the paper money used for the purchase of chips, or the amount of paper money paid out in correspondence with the chips purchased, after the purchase of chips with paper money, to determine whether the amount of chips grasped in the chip tray of the dealer of the game table is reduced.

[0027] In the above-described fraud detection system, the control device can further include a database in which a purchase history of chips purchased with paper money is recorded, and can compare the amount of chips grasped in the chip tray of the dealer of the game table with the total amount of chips paid out in correspondence with the paper money used for the purchase of chips, or the amount of paper money paid out in correspondence with the chips purchased, with reference to the database at a certain time or on a daily basis.

[0028] In the above-described fraud detection system, the control device can determine the player at the play position extracted as the difference or abnormality by means of the image analysis device.

[0029] In the above-described fraud detection system, the control device can have a warning function of notifying the presence of the specific player to another game table when the determined player leaves the game table and sits at the other game table.

[0030] In the above-described fraud detection system, the control device can further include a function of determining at least one of:

[0031] 1) whether there is no change in chips during a period from the start of the card draw or from the start of the dealer's game operation to the display of the win or loss result of the game by the card dispensing device in each game,

[0032] 2) whether the loser among the game participants does not take the chips during the period in which the dealer recovers the chips placed by the loser after the end of each game,

[0033] 3) whether chips are added during the period in which the dealer recovers the chips placed by the loser among the game participants after the end of each game,

[0034] 4) whether the dealer pays the position of the chips placed by the winner among the game participants after the end of each game,

[0035] 5) whether the winner among the game participants takes the placed chips and the paid chips after the end of each game.

[0036] In the fraud detection system described above, the win / loss result determination device can be a card dispensing device that dispenses cards at the game table, or a control device that determines the win / loss result of each game based on information from the image analysis device that reads the cards dispensed at the game table using a camera.

[0037] Effects of the invention

[0038] The fraud detection system according to the present application can detect fraud in the collection and payout of gaming chips based on the win / loss result of the game.

[0039] Furthermore, the system according to the present application can determine the size and suit of a card even if the card is bent due to the player's repeated pressing of the card in a card game or the like, and can grasp the total amount and position of gaming chips even if there are blind spots and overlapping gaming chips. Furthermore, the system can detect fraud when gaming chips are purchased with paper money. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 FIG. 1 is a diagram showing an overview of a fraud detection system in a game arcade having a plurality of game tables according to a first embodiment of the present application.

[0041] Figure 2A FIG. 3 is a perspective view of a gaming chip showing examples of different overlapping states of the gaming chip grasped in the first embodiment of the present application.

[0042] Figure 2B FIG. 4 is a perspective view of a gaming chip showing examples of different overlapping states of the gaming chip grasped in the first embodiment of the present application.

[0043] Figure 3A FIG. 5 is a diagram showing a detailed situation of a gaming chip tray according to the first embodiment of the present application.

[0044] Figure 3B FIG. 6 is a diagram showing another example of a gaming chip tray according to the first embodiment of the present application.

[0045] Figure 4 FIG. 7 is an enlarged view of a mark for explaining dirt on a card grasped in the first embodiment of the present application.

[0046] Figure 5A FIG. 8 is a plan view of the front of a logo according to the first embodiment of the present application.

[0047] Figure 5B FIG. 9 is a plan view of the back of a logo according to the first embodiment of the present application.

[0048] Figure 6is a diagram for explaining a video of a purchase state of a game chip purchased with a banknote, which is grasped in the first embodiment of the present application.

[0049] Figure 7 is a plan view showing an outline of a cheating detection system of a certain card game in the second embodiment of the present application.

[0050] Figure 8 is a plan view showing an outline of a progress state of a certain card game in the cheating detection system of the second embodiment of the present application.

[0051] Figure 9 is a diagram showing a case of a collection of a game chip won by a dealer in a certain card game.

[0052] Figure 10 is a diagram showing a case of a payment to a guest (game participant) who won in a certain card game in the second embodiment of the present application.

[0053] Figure 11 is a diagram showing a case of a collection of a game chip won by a dealer in a certain card game.

[0054] Figure 12A is a diagram showing a case of a collection of a game chip won by a dealer in a certain card game.

[0055] Figure 12B is a diagram showing a case of a collection of a game chip won by a dealer in a certain card game.

[0056] Figure 12C is a diagram showing a case of a collection of a game chip won by a dealer in a certain card game.

[0057] Figure 13 is a diagram showing a case of a collection of a game chip won by a dealer in a certain card game.

[0058] Figure 14A is a diagram showing a case of a collection of a game chip won by a dealer in a certain card game.

[0059] Figure 14Bis a diagram of an image that becomes an object of image analysis of the collection of game chips won by a game participant in the fraud detection system of the second embodiment of the present invention.

[0060] Figure 14C is a diagram of an image that becomes an object of image analysis of the collection of game chips won by a game participant in the fraud detection system of the second embodiment of the present invention.

[0061] Figure 14D is a diagram of an image that becomes an object of image analysis of the collection of game chips won by a game participant in the fraud detection system of the second embodiment of the present invention.

[0062] Figure 15 is a side cross-sectional view of the card dispensing device in the second embodiment of the present invention.

[0063] Figure 16 is a diagram showing an example of a card in the second embodiment of the present invention.

[0064] Figure 17 is a diagram of a partial cross-sectional view of the card guiding portion of the card dispensing device in the second embodiment of the present invention.

[0065] Figure 18A is a diagram showing a partial side cross-sectional view of a dispensing restriction device that restricts the entry and exit of a card from a card housing portion of the card dispensing device in the second embodiment of the present invention.

[0066] Figure 18B is a diagram showing a partial side cross-sectional view of a dispensing restriction device that restricts the entry and exit of a card from a card housing portion of the card dispensing device in the second embodiment of the present invention.

[0067] Figure 19 is a diagram showing the relationship between the output waveform of a sensor and a mark in the card dispensing device in the second embodiment of the present invention. DETAILED DESCRIPTION

[0068] (First Embodiment)

[0069] In an entertainment venue or the like, game chips are stacked high and placed on a game table, but there is a problem that the total amount cannot be accurately read by an IC tag reading device provided under the game table, and if the sensitivity of the reading device is increased, there is a problem that game chips placed in different positions (winning or losing by position) are aggregated, and the total amount of game chips in each position cannot be grasped. Also, there is a problem that the total amount of game chips cannot be grasped due to a dead angle formed by the angle of view of a camera or being blocked by overlapping for shooting from the camera.

[0070] Moreover, although it is often performed in a certain card game, there is a problem that a card is bent due to a player's pressing of the card (a behavior of bending a card with the back surface up, looking at the card face size little by little while expecting it, and the like) and the like, and the card face size and the color of the card cannot be determined by image analysis from a camera.

[0071] Moreover, a new problem that cheating on a game table is becoming more sophisticated, and cheating based on a sophisticated placement method and the like that cannot be found by simply detecting a larger amount won and the like on the game table, and the like cannot be found by a camera and tracking of the amount won is also grasped. Moreover, cheating based on collusion between a dealer and a player cannot be sufficiently prevented by the prior art.

[0072] To solve the above various problems, a cheating detection system of a game house having a plurality of game tables according to a first embodiment,

[0073] is a cheating detection system in a game house having a plurality of game tables, and includes:

[0074] a game recording device that records a progress state of a game performed at the game table, including a dealer and a player, as an image by a camera;

[0075] an image analysis device that performs image analysis on the recorded image of the progress state of the game;

[0076] a card dispensing device that determines and displays a win or loss result of each game at the game table; and

[0077] a control device that detects cheating at the game table using a result of the image analysis by the image analysis device and the win or loss result determined by the card dispensing device.

[0078] In addition, in the cheating detection system, the card dispensing device is configured to be able to read a card face size of a dispensed card, and the control device is configured to be able to determine agreement or disagreement by collating information of the card face size obtained by the image analysis device from an image of each card dispensed at the game table and information of the card face size read by the card dispensing device.

[0079] In addition, in the cheating detection system, the image analysis device or the control device is an artificial intelligence effective use type or a deep learning configuration that is able to obtain information of a card face size from a card dispensed at the game table and bent or soiled by a player.

[0080] Further, in the fraud detection system, the control device grasps the position, kind, and number of game coins placed by each player by means of the image analysis device, and determines whether the collection of the lost game coins placed by each player and the payment of the won game coins are performed correctly in accordance with the win / loss result of the game by analyzing the image of the game progress state by means of the image analysis device.

[0081] Further, in the fraud detection system, the image analysis device or the control device is an artificial intelligence effectively utilized type or a deep learning configuration capable of obtaining information on the kind, number, and position of the placed game coins even when a plurality of game coins placed on the gaming table are hidden in a state of being partially or entirely hidden due to a blind spot of the camera.

[0082] Further, in the fraud detection system, the control device is an artificial intelligence effectively utilized type or a deep learning configuration capable of comparing the amount of the grasped game coins in the game coin tray of the dealer of the gaming table in accordance with the win / loss result of the game, and determining whether the amount of the collected lost game coins placed by each player and the amount of the paid won game coins are increased or decreased after the game ends and is settled.

[0083] Further, in the fraud detection system, the control device is an artificial intelligence effectively utilized type or a deep learning configuration capable of grasping the position and amount of the game coins placed at each play position of the gaming table, comparing the win / loss history of each player obtained from the win / loss result of each game and the obtained amount of game coins with statistical data of past games, and extracting as an abnormal situation.

[0084] Further, in the fraud detection system, the control device is an artificial intelligence effectively utilized type or a deep learning configuration capable of comparing the amount of the placed game coins at the time of loss at a play position of a certain gaming table with the amount of the placed game coins at the time of win, and extracting as an abnormal situation.

[0085] Further, in the fraud detection system, the control device is a configuration capable of determining, as the abnormal situation extracted by means of the image analysis device, or obtaining a win of a prescribed amount or more at a play position of an individual player.

[0086] Further, in the fraud detection system, the control device has a warning function of notifying the presence of the specific player to another gaming table when the determined player leaves the seat and sits at the other gaming table.

[0087] To solve the above-described various problems, the fraud detection system in a gaming house having a plurality of gaming tables according to the present application has:

[0088] a game recording device that records the progress state of the game performed at the gaming table, including a dealer and players, as an image by a camera;

[0089] a card dispensing device that determines and displays the win or loss result of each game at the game table;

[0090] an image analysis device that performs image analysis on the recorded video of the game progress state; and

[0091] a control device that can detect paper money and gaming chips at the game table using the image analysis result of the image analysis device;

[0092] The image analysis device or the control device is an artificial intelligence effective utilization type or a deep learning configuration that, based on information obtained from the card dispensing device or the dealer, can detect that paper money is being used to purchase gaming chips at the game table in a situation other than card distribution, and recognize the total amount of the paper money that has passed near-ultraviolet light verification, and further recognize the total amount of gaming chips even if a plurality of gaming chips taken out at the game table as a purchase object are hidden in a state where part or the entire gaming chips are hidden in a blind spot of the camera, and can compare the total amount of paper money taken out by players at the game table and the total amount of gaming chips taken out by the dealer, and determine whether the amounts are consistent.

[0093] In addition, in the fraud detection system, the control device is an artificial intelligence effective utilization type or a deep learning configuration that can compare the amount of gaming chips grasped in the gaming chip tray of the dealer at the game table with the amount of gaming chips that have been reduced based on the payout amount of the paper money used for the purchase after the purchase of gaming chips with paper money and the settlement.

[0094] In addition, in the fraud detection system, the control device is an artificial intelligence effective utilization type or a deep learning configuration that can compare the amount of gaming chips grasped in the gaming chip tray of the dealer at the game table with the amount of gaming chips that have been reduced based on the payout amount of the paper money used for the purchase after the purchase of gaming chips with paper money and the settlement.

[0095] The fraud detection system according to the present embodiment can determine the size and color of the card face even if the card is bent due to the player's pressing of the card in a card game or the like, and can grasp the total amount and position of gaming chips even for gaming chips in a blind spot and overlapping. Furthermore, fraud when purchasing gaming chips with paper money can also be detected.

[0096] The following describes the outline of the overall cheating detection system in the casino with multiple gaming tables according to the first embodiment of the present application in further detail. Figure 1 is a diagram showing the outline of the overall system, the cheating detection system in the casino with multiple gaming tables 4, provided with: a game recording device 11 that records the progress of the game played at the gaming tables 4, including the players 6 and the dealers 5, as video images by multiple video cameras 2; an image analysis device 12 that performs image analysis on the recorded video images of the progress of the game; and a card distribution device 3 that determines and displays the win / loss result of each game at the gaming tables 4. The card distribution device 3 is a so-called electronic shoe that has been used by those skilled in the art, configured to pre-program the rules of the game, capable of reading the information of the distributed cards C, and determine the win / loss of the game. For example, in a certain card game, the win / loss result is basically determined by the face value of 2-3 cards, and the determination result (win / loss result) is displayed by the result display lamp 13.

[0097] The present cheating detection system is further provided with a control device 14 that compares the actual face value of the cards based on the image analysis result of the image analysis device 12 and the win / loss result determined by the card distribution device 3, and detects the cheating behavior (inconsistency between the total face value of the distributed cards and the win / loss result, etc.) performed at the gaming tables 4. The card distribution device 3 is configured to be capable of reading the face value (A, 2-10, J, Q, K) and the suit (heart, spade, etc.) of the cards C manually distributed by the dealer 5, and the control device 14 is configured to be capable of collating the information of the face value and the suit obtained by the image analysis device 12 (using artificial intelligence) from the video images (captured using the video cameras 2) of each card distributed at the gaming tables 4, and the information of the cards and the suits read by the card distribution device 3, and determining the consistency or inconsistency. The image analysis device 12 and the control device 14 in the present cheating detection system are configured integrally or in combination with a computer, a program, and a memory composed of multiple structures.

[0098] The image analysis device 12 and the control device 14 are provided with an artificial intelligence effective utilization type or deep learning configuration that is capable of obtaining the information of the face value of the cards even when the cards C distributed at the gaming tables 4 are bent or soiled by the players 6. The soiled cards C are as follows Figure 4As shown, a situation occurs in which it is difficult to determine whether it is a spade or a club. Even in such a case, by using an artificial intelligence effective utilization type computer or control system, image analysis, determination using a deep learning (construction) technique, it is possible to determine the suit. Furthermore, even if the card is bent due to the player's pressing of the card in a card game or the like, by using self-learning of a plurality of image deformation examples or the like, by an artificial intelligence effective utilization type computer or control system, deep learning (construction) technique, it is possible to recognize the suit and the card face size of the card before deformation. The artificial intelligence effective utilization type computer or control system, deep learning (construction) technique is already known and can be used by those skilled in the art, so a detailed description is omitted.

[0099] The control device 14 of the specific artificial intelligence effective utilization type or deep learning construction can grasp, by the camera 2, the image analysis device 12, which position (P, or B, or PAIR) of the placement area 8 each player 6 places the chip 9, the type (the chip 9 is assigned a different amount of value for each color) and the number of chips 9 placed. There are not only cases where the chips 9 are arranged vertically and overlap, but also cases where they are offset and overlap as shown in Figure 2A The camera 2 is located in the direction of the arrow X as shown Figure 2A As shown in Figure 2B It can be assumed that the chip 9 cannot be seen (goes into a blind spot). The artificial intelligence effective utilization type computer or control system, deep learning (construction) technique can use a self-learning function or the like to recognize the concealment of the chip 9 due to the blind spot or the like (a case where part of the chip is concealed, or a case where the entire chip is concealed), and accurately grasp the number or the like. In this way, since it is possible to grasp which position (P, or B, or PAIR) of the placement area 8 the chip 9 is placed, the type (the chip 9 is assigned a different amount of value for each color) and the number of chips 9 placed, in each game, in accordance with the game win / loss result determined by the card distribution device 3, the control device 14 determines whether the collection of the lost chip placed by each player 6 (indicated by the arrow L) and the payment of the won chip to the player 6W who won (9W) are correctly performed in accordance with the game win / loss result by analyzing the image of the game progress state by the image analysis device 12.

[0100] The control device 14 can grasp the total amount of the chips 9 in the chip tray 17 of the dealer 5 of the game table 4 using the image analysis device 12, and can compare the calculated amount of the recovery of the lost chips 9 and the payment 9W of the won chips to the players 6W after the game ends and the settlement is made, and can determine whether the total amount of the chips 9 in the chip tray 17 is increased or decreased according to the win or loss result of the game. Even if the total amount of the chips 9 in the chip tray 17 is grasped all the time by means of RFID or the like, whether the increase or decrease is correct is determined by the control device 14 by analyzing the image of the game progress state with the aid of the image analysis device 12. These also effectively utilize the artificial intelligence effective utilization type or deep learning configuration.

[0101] In this example, since the win or loss result of the game, the information of which kind of chip 9 is placed how many times to which position (P, or B, or PAIR) of the placement area 8, and the increase or decrease of the chips 9 in the chip tray 17 after the recovery of the lost chips and the payment of the won chips are detected, even if the movement of the chips 9 after the game ends, i.e., the placed chips 9 are moved to the player side or to the dealer side, is not grasped, the cheating or error can be detected.

[0102] Here, for example in the case of a certain card game, the win or loss result of the game can be determined according to the rules of the certain card game by reading the card face size of the cards C dealt one after another by the card dealing device 3 in the game. Also, the win or loss result of the game can be determined by the control device 14 by comparing the analysis result with the rules of the game using the image analysis device 12 by shooting the game on the game table 4 with the camera 2 and analyzing the image. In this case, the win or loss result determination device is constituted by the camera 2, the image analysis device 12, and the control device 14. The information of which kind of chip 9 is placed how many times to which position (P, or B, or PAIR) of the placement area 8 by the players at each play position 7 can be obtained by shooting the chips 9 placed to the placement area 8 with the camera 2 and analyzing the image by the image analysis device 12 for each play position 7.

[0103] Moreover, the increase and decrease of the game coins 9 in the game coin tray 17 before and after the collection of the game coins 9 of the loss and the payment of the game coins 9 of the win can be calculated by comparing the total amount of the game coins 9 in the game coin tray 17 before the collection of the game coins 9 of the loss and the payment of the game coins 9 of the win with the total amount of the game coins 9 in the game coin tray 17 after the collection of the game coins 9 of the loss and the payment of the game coins 9 of the win. The total amount of the game coins 9 in the game coin tray 17 before the collection of the game coins 9 of the loss and the payment of the game coins 9 of the win and the total amount of the game coins 9 in the game coin tray 17 after the collection of the game coins 9 of the loss and the payment of the game coins 9 of the win can be detected by the image analysis device 12 analyzing the images captured by the camera 2 of the game coin tray 17 in which the game coins 9 are stored. Alternatively, the total amount of the game coins 9 in the game coin tray 17 can be detected by embedding an RFID indicating the amount of the game coins 9 in the game coins 9 and providing an RFID reader on the game coin tray 17.

[0104] For example, let the total amount of the game coins 9 in the game coin tray 17 before the game starts be Bb, and the total amount of the game coins 9 in the game coin tray 17 after the game ends and the collection of the game coins of the loss and the payment of the game coins of the win ends be Ba. In addition, in this game, the total amount of the game coins 9 in all the play positions 7 placed in the P area is bp, the total amount of the game coins 9 in all the play positions 7 placed in the B area is bb, and the total amount of the game coins 9 in all the play positions 7 placed in the tie area is bt. For example, in the case where the result of the game is B wins, Ba-Bb=bp-bb+bt should be established. Alternatively, the total amount of the game coins 9 in the game coin tray 17 after the game ends Ba should be (Bb+bp-bb+bt). In the case where this is not true, it can be determined that there is a fraud or an error in the collection or the payment of the game coins.

[0105] Figure 3A is a diagram showing the detailed situation of the game coin tray of the present embodiment, Figure 3Bis a view showing other examples of the chip tray. In the chip tray 17, a recovered chip tray 171 that recovers and temporarily stores the chips 9L placed by the losing player 6L and a paid-out chip tray 172 that stores the chips 9W to be paid out are provided. The image analysis device 12 and the control device 14 grasp the position, kind, and number of the chips 9L placed by the losing player 6L, calculate the amount of the chips 0L in the game (the proper amount of the chips 9 in the recovered chip tray 171), and further grasp the actual total amount of the chips 9 in the recovered chip tray 171 after the recovery. The total amount and the actual total amount are compared to determine whether there is a difference.

[0106] In addition, by using the chips 9 in the paid-out chip tray 172 for the payout of the chips 9W to the winning player 6W, sufficient time can be ensured for the image analysis device 12 and the control device 14 to grasp the actual total amount of the chips 9 in the recovered chip tray 171 after the recovery.

[0107] The game table 4 is provided with a discard area 41 and / or a discard slot 42 for discarding the cards C used in the game. The cards C used in the game are recovered at the end of each game and discarded in the discard area 41 or the discard slot 42 on the game table 4.

[0108] The game table 4 is further provided with a marker 43 that shows the win or loss of the game. Figure 5A is a plan view of the front surface of the marker, Figure 5B is a plan view of the back surface of the marker. In some card games, two kinds of markers 43a and 43b showing P win and B win are used, and the dealer 5 turns over the marker of the winning side of P or B when the game result is determined. Thus, the win or loss of the game is easily displayed on the table. The turned-over marker is restored by the dealer 5 after the recovery and payout of the chips 9 are completed. By restoring the marker, it also means that the state in which the next game can be started is achieved.

[0109] As described above, in the present embodiment, the control device 14 calculates the balance of the chips according to the amount of the chips placed on the game table 4 and the win or loss result of the game for each game, and verifies the increase in the balance of the chips in the chip tray 17 after the game. If the control device 14 detects a difference in the verification, an alarm is issued, or a record indicating the situation is added to the record of the video captured by the video camera 2. The casino operator can investigate the cause of the difference by checking the video.

[0110] The cheating detection system of the present embodiment compares the expected total amount of game chips 9 in the game chip tray 17 after settlement at the end of the game with the actual total amount of game chips 9 in the game chip tray 17 at the end of the game obtained by the image analysis device 12, and determines whether there is a difference between the expected total amount and the actual total amount.

[0111] The control device 14 grasps the position, kind, and number of game chips placed by each player by means of the image analysis device 12, grasps the actual total amount of game chips in the game chip tray at the end of the collection of all the lost game chips placed by the players, and compares the expected total amount of game chips 9 in the game chip tray 17 obtained from the total amount of game chips 9 in the game chip tray before settlement of each game, to which the increase in the game chip tray 17 in the game is added according to the position, kind, and number of game chips placed by the losing players, with the actual total amount of game chips 9 in the game chip tray 17, and determines whether there is a difference between the expected total amount and the actual total amount.

[0112] The control device 14 determines that there is a payment error when the expected total amount of game chips 9 in the game chip tray 17 obtained from the total amount of game chips 9 in the game chip tray before settlement of each game, to which the increase in the game chip tray 17 in the game is added according to the position, kind, and number of game chips placed by the losing players, is compared with the actual total amount of game chips 9 in the game chip tray 17, and it is determined that there is no difference between the expected total amount and the actual total amount, and the expected total amount in the game chip tray 17 after settlement at the end of the game is compared with the actual total amount of game chips 9 in the game chip tray 17 at the end of the game obtained by the image analysis device 12, and it is determined that there is a difference between the expected total amount and the actual total amount.

[0113] In the game chip tray 17, a collection game chip tray 171 that collects and temporarily stores game chips 9 placed by the losing players is provided, and the image analysis device 12 compares the expected total amount of game chips 9 in the collection game chip tray 171 obtained by adding the increase in game chips 9 in the game calculated according to the position, kind, and number of game chips 9L placed by the losing players to the expected total amount of game chips 9 in the collection game chip tray 171 after the addition, with the actual total amount of game chips 9 in the collection game chip tray 171, and determines whether there is a difference between the expected total amount and the actual total amount.

[0114] When the control device 14 determines that the actual total amount of the grasped chips 9 in the chip tray 17 of the dealer 5 of the game table 4 does not correspond to the increase or decrease amount of chips calculated from the total amount of chips placed by all players and the win or loss result of the game, the game record device 11 is capable of analyzing the record of the game in which the above difference is generated, and the game record device 11 is configured to attribute an index or a time to the acquired image, or capable of determining and reproducing the chip 9 recovery scene or the payout scene.

[0115] Thus, the control device 14 obtains the total amount of chips in the chip tray 17 after clearing at the end of the game by means of the image analysis device 12, but the determination after clearing in the so-called case is at the time when any one of the following 1) to 4) occurs:

[0116] 1) at the time of the end of the payout of the won chips 9;

[0117] 2) at the time of the recovery and disposal of the card C used in the game in the disposal area 41 or the disposal slot 42 of the table;

[0118] 3) at the time of pressing the prescribed button attached to the win or loss determination device;

[0119] 4) at the time of the restoration of the win or loss indicator 43.

[0120] Further, the control device 14 is an artificial intelligence effective utilization type or deep learning configuration capable of grasping the position (position placed for P, or B, or PAIR) and the amount (kind and number) of chips placed at each play position 7 of the game table 4, comparing the win or loss history of each player 6 obtained from the win or loss result of each game and the obtained amount of chips (won amount) with the statistical data of many (big data) games in the past, and extracting as an abnormal condition (set by the casino). Typically, it is a device of the control device 14 having an artificial intelligence effective utilization type or deep learning configuration capable of extracting as an abnormal condition by comparing the generation of a certain amount (100 million points) or more of the won amount, or the state in which the amount of chips placed at the time of loss at a certain game table 4 is small and the amount of chips placed at the time of win is large, which continues in a plurality of games, with the statistical data (big data, etc.) of past games.

[0121] Further, the control device 14 (integral with the image analysis device 12) of the present cheating detection system is capable of determining the configuration of the individual player 6 on the play position 7 on which an abnormal condition is extracted or a win of a prescribed amount or more is obtained. For the determination of such a player 6, in the image analysis device 12, the image of the face is obtained by the feature point extraction or the like, and is determined by assigning an identification number (ID or the like). Also, the control device 14 has a warning function of notifying the existence of the specific player to another gaming table when the determined player 6 leaves the seat and sits at another gaming table. Specifically, the manager or the table manager (may be a dealer) who manages each gaming table 4 is notified to prevent more abnormal phenomena.

[0122] The control device 14 also has a database in which the purchase history of the game chips 9 purchased with the banknotes K is recorded, and refers to the database to compare and determine whether the amount of the game chips 9 grasped in the game chip tray 17 of the dealer 5 of the gaming table 4 is reduced according to the total amount of the payout amount of the game chips 9 corresponding to the banknotes K used for the purchase or the payout amount of the banknotes K corresponding to the purchased game chips 9, at a certain time or at a unit of a day.

[0123] Also, in the above example, the win / loss history and the amount of the game chips obtained (win amount) for each play position 7 can be monitored without determining the individual player 6. In this case, although the individual player 6 cannot be tracked and investigated when the player 6 leaves the seat, it is possible to detect an abnormal condition in which the amount of the game chips placed is small when losing and the amount of the game chips placed is large when winning at a specific play position 7 of one gaming table 4 continues in multiple games. Also, in the case where such a play position 7 is detected, it is suspected that there is cheating or error at the play position 7. Also, by verifying the video of the play position 7, it is possible to find the cheating or error.

[0124] Specifically, the camera 2 is arranged to take an image of at least the chips 9 placed in the placement area 8 of each user position 7. The image analysis device 12 analyzes the image taken by the camera 2, and detects, for each user position 7, which position (P, B, or draw) of the placement area 8 is placed with a chip and the amount of chips placed. Further, the card distribution device 3 functions as a win / loss result determination device, and determines the win / loss result of the game. The control device 14 records (monitors) the win / loss history and the amount of chips obtained (chip gain) for each user position 7 based on the position (P, B, or draw) of the placement area 8 where the chip 9 is placed and the win / loss result of the game. Further, only one of the win / loss history and the chip gain can be recorded. The control device 14 determines the user position 7 as a user position suspected of having committed fraud when the win / loss history and / or the chip gain history is compared with the statistical data of many (large data) games in the past and is found to be an abnormal condition (set by the casino).

[0125] When a user position 7 is suspected of having committed fraud, the fraud detection system can generate an alarm (light, sound, or vibration) in a manner that at least the dealer can perceive at the time point. Thus, the continuation of the fraud can be prevented by interrupting the game or the like at least in the place. Further, information indicating that the fraud is suspected can be added to the video taken and recorded by the camera 2. Thus, the cause of the suspected fraud can be investigated by confirming the video.

[0126] The fraud detection system in the casino having the game table according to the present embodiment also has a function of performing inspection at the time of the purchase of chips with paper money and the game of chips repeatedly performed at the game table 4. In the casino or the like, before the game, the user 6 purchases chips with paper money (cash or the like) at a prescribed chip purchase place. However, when the user 6 runs out of chips, the user 6 can continue the game after purchasing chips 9 with cash (paper money) at the game table (a certain card game table or the like) without leaving the game table 4. However, this can create an opportunity for the dealer 5 and the user to commit fraud. The purchase of chips 9 with cash (paper money) at the game table (a certain card game table or the like) needs to be performed when the game is not performed. The card distribution device 3 can detect the start and end of the card division (period of determination of win / loss) in order to determine the win / loss of the game. Therefore, the control device 14 detects that the purchase of chips 9 with paper money is being performed at the game table 4 in a situation other than the card division (described below) in the card distribution device 3. The card division (or the situation other than the card division) can be detected based on information obtained from the actions of the card distribution device 3 or the dealer 5. Figure 6 Thus, the continuation of the fraud can be prevented by interrupting the game or the like at least in the place. Further, information indicating that the fraud is suspected can be added to the video taken and recorded by the camera 2. Thus, the cause of the suspected fraud can be investigated by confirming the video.

[0127] The control device 14 performs image analysis of the surface of the bill K, and can recognize the number and the amount of the bill. Further, on the game table 4, whether the bill K used for purchasing the gaming chip 9 is a true bill or not is verified by irradiating near-ultraviolet light to detect the authenticity mark G of the bill. As shown in FIG. 6, the control device 14 is an artificial intelligence effective utilization type or a deep learning configuration that verifies the authenticity mark G also by image analysis, recognizes the total amount of the true bill, and further can recognize the total amount of the gaming chip even if a plurality of gaming chips taken out on the game table as a purchase object become hidden states due to the dead angle of the camera 2, can compare the total amount of the bill K taken out on the game table 4 from the player with the total amount of the gaming chip 9 taken out from the dealer 5, and determine whether the amounts of the two are consistent or not. Figure 6

[0128] The control device 14 is an artificial intelligence effective utilization type or a deep learning configuration that can compare and calculate the total amount of the gaming chip 9 in the gaming chip tray 17 of the dealer 5 of the game table 4, and whether the total amount is reduced according to the payout amount of the gaming chip corresponding to the bill used for purchase after the purchase of the gaming chip with the bill and the settlement. It is also possible to consider a case where the total amount of the gaming chip 9 in the gaming chip tray 17 of the dealer 5 is always grasped in advance using the RFID of the gaming chip 9. In addition, by capturing the gaming chip tray 17 in which the gaming chip 9 is accommodated using the camera 2, and analyzing the image using the image analysis device 12, it is also possible to detect the total amount of the gaming chip 9 accommodated in the gaming chip tray 17.

[0129] Further, the control device 14 verifies whether the reduction of the amount of the gaming chip 9 in the gaming chip tray 17 before and after the purchase of the gaming chip with the bill is consistent with the payout amount of the gaming chip on the game table 4 by image analysis. As for the amount of the bill that has been paid, it can be input to the control device 14 by the dealer 5 through the keyboard input or the like, or it can be determined by capturing the game table 4 on which the bill is paid using the camera 2, and analyzing the image using the image analysis device 12.

[0130] As described above, the control device 14 determines whether the reduced portion of the gaming chip 9 in the gaming chip tray 17 due to the purchase of the gaming chip with the bill is consistent with the amount of the bill paid to the dealer 5 by the player 6. Further, the control device 14 is an intelligent control device that can compare and calculate whether the total amount of the bill based on the amount of the bill received by the dealer 5 (usually based on the keyboard input or the like) and the calculated amount of the bill based on the image analysis result of the image analysis device 12 are consistent or not after the purchase of the gaming chip with the bill and the settlement, and further can be an artificial intelligence effective utilization type or a deep learning configuration.

[0131] ​Further, the control device 14 is an artificial intelligence effective use type or a deep learning configuration that can compare and calculate the consistency or inconsistency of the total amount of the paper money input by the dealer in the game table 4 with the total amount of the paper money based on the image analysis result of the image analysis device 12.

[0132] The control device 14 compares and determines whether the amount of the chips 9 grasped in the chip tray 17 of the dealer 5 of the game table 4 is reduced according to the payout amount of the chips 9 corresponding to the paper money used for the purchase of the chips 9 or the payout amount of the paper money corresponding to the purchased chips 9 after the purchase of the chips 9 with the paper money.

[0133] (2nd Embodiment)

[0134] In most of the table games performed in the game rooms and the like, there is a certain card game. These games use a standard deck of 52 playing cards, and a card dispensing device provided with a plurality of decks (6 to 9 or 10 decks) that are pre-shuffled dispenses the playing cards to the game table, and the win or loss is determined according to the number (card face size) of the dispensed cards and the game rules.

[0135] The dispensing of the cards from the card dispensing device and the calculation of the amount of the bet of the customer (game participant) are performed by the dealer and the like in charge of the game table. In the game rooms and the like, attempts are being made to prevent errors and fraudulent acts in the calculation of the amount of the bet of the customer (game participant).

[0136] In the card game monitoring system described in International Publication WO2015 / 107902, the change in the chips is read using a monitoring camera, and it is checked whether the amount of the bet is paid to the winner.

[0137] Regarding the bet of the customer in a certain card game and the calculation of the amount of the bet of the customer (game participant) by the dealer, there is a problem that it cannot be detected when these are performed, who places the chips, or whether it has been taken away, and thus it cannot be grasped whether these are correct.

[0138] To solve the above-described problems, the fraud detection system of the 2nd embodiment is a fraud detection system of a game room having a game table, and includes:

[0139] a game monitoring device that monitors the progress of the game performed at the game table using a camera;

[0140] an image analysis device that performs image analysis on the video obtained using the camera;

[0141] a card dispensing device that determines and displays the win or loss result of each game at the game table; and

[0142] a control device that determines the position of the chips placed on the table by the game participants in each game using the analysis result of the image analysis device, and determines the winner and the loser among the participants in each game using the win / loss result;

[0143] The control device further has a function of determining at least one of:

[0144] 1) whether there is no change in the chips during a period from the start of the card draw or from the game start operation of the dealer to the display of the win / loss result of the game by the card dispensing device in each game,

[0145] 2) whether there is no change in the chips caused by a person other than the dealer during a period in which the dealer collects the chips placed by the losers among the game participants after the end of each game,

[0146] 3) whether chips are added during a period in which the dealer collects the chips placed by the losers among the game participants after the end of each game,

[0147] 4) whether the dealer pays the chips placed by the winners among the game participants after the end of each game,

[0148] 5) whether the winners among the game participants take the placed chips and the paid chips after the end of each game.

[0149] Further, the control device can be configured to determine at least one of 1) to 5) by detecting the change in the hands of the dealer and the game participants, the change in the chips, or the change in the hands and the change in the chips using the analysis result of the image analysis device.

[0150] Further, the control device can be configured to determine whether the amount of chips paid by the dealer to the winners among the game participants is correct according to the amount placed by the winners.

[0151] Further, the game fraud detection system can further have a monitor or a light that receives the determination result and performs warning or display.

[0152] The fraud detection system according to the present embodiment can detect the time when the placement by the guest and the calculation of the amount of the placement by the dealer for the guest (game participant) in a certain card game are performed, who placed the chips, or whether the chips have been taken, can detect the error and the fraud behavior and perform warning or display, and can prevent the recurrence.

[0153] Before proceeding to the detailed description of this embodiment, the process of a certain card game played in amusement parks such as casinos will be described. Furthermore, in this second embodiment, the same components as in the first embodiment will be described with the same numbering.

[0154] like Figure 7 As shown, at game table 4, the guest (game participant / player) 6 and the dealer 5 sit facing each other at the playing position (chair) 7. The guest (game participant) 6 places game coins 9 in the placement area 8 in front of them, placing them to determine the outcome of a card game, whether P (PLAYER) or B (BANKER) wins, or results in a tie (TIE). The dealer 5 times the timer to complete the placement by the guest (game participant) 6, shouting "No More Bet (placement completed)," and making actions such as moving their hand horizontally. Figure 7 (The state shown in the image). In a certain card game, from the moment the card draw begins ("No More Bet" is called, or the dealer 5 starts the game), until the game results are displayed via the card dispensing device 3, the guest (game participant) 6 cannot move game coins, place additional game coins, or retrieve placed game coins.

[0155] Next, the game cards 1 are drawn one by one from the card dispensing device 3, face down, and placed onto the game table 4. First, four cards are drawn, such as... Figure 8 As shown in ① to ④, the first card belongs to P (PLAYER), the second card to B (BANKER), the third card to P (PLAYER), and the fourth card to B (BANKER), arranged in areas 10 (P area 10P and B area 10B) visible from the dealer 5 at game table 4. Furthermore, based on the face value (number) of the first to fourth cards 1 and the conditions in the detailed rules of a certain card game, the dealer 5 draws the fifth and sixth cards 1, which belong to either P (PLAYER) or B (BANKER). Then, based on the face value (number) of the first to fourth cards 1 (and, depending on the situation, the fifth and sixth cards) and the detailed rules of a certain card game, the winner of the game is determined. Here, the card dispensing device 3 is configured to pre-program the game rules, enabling it to read the information of the dispensed cards 1 (card rank (number) and suit) to determine the winner. A determination is made as to whether the winner / loser result determined by the card dispensing device 3 is consistent with the winner / loser result determined by the dealer, etc., as described above.

[0156] The following is an overview of the cheat detection system in an amusement park according to an embodiment of the present invention.Figure 7 is a diagram showing an overview of the entire system, the cheating detection system in the game in the casino is provided with: a game recording device 11 that records the progress of the game being played at the gaming table 4, including the guests (game participants) 6 and the dealer 5, as video by the video camera 2; an image analysis device 12 that performs image analysis on the video of the progress of the game being recorded; and a card dispensing device 3 that has a function of determining and displaying the win or loss result of each game at the gaming table 4. The card dispensing device 3 is a so-called electronic shoe that has been used by those skilled in the art, configured to program the rules of the game in advance, can detect the time when the card 1 is dispensed at the start of each game by the dealer 5, and read the information (card face size (number) and suit) of each card 1 dispensed to determine the win or loss of the game. For example, in a certain card game, for B win, P win, and tie (draw), the determination result (win or loss result) is basically determined by the card face size of 2-3 cards, respectively, and is displayed by the display light 13.

[0157] The control device 14 of the present cheating detection system is provided with a game chip detection function that determines which of the P side or B side placement area 8 the guest 6 (game participant) placed the game chip 9 on at the gaming table 4 using the analysis result of the image analysis device 12 in each game. As for the position and total amount of the game chip 9 (which of the P side or B side placement area 8 the game chip 9 is placed on), it is assumed that it cannot be read in general in the case where the game chip 9 is overlapped or falls into a blind spot from the position of the video camera 2, etc. The control device 14 is configured to be able to recognize the concealment of the game chip 9 due to the blind spot (the case of partial concealment of one game chip, or the case of total concealment of the game chip), accurately grasp the position and number, etc. using self-learning functions, etc. based on existing artificial intelligence effective utilization type computers or control systems, deep learning (configuration) techniques, etc. Furthermore, the configuration for detecting the position and type in the placement area 8 of the game chip 9 is not limited thereto, and can be configured to detect by reading the ID embedded in the game chip, for example.

[0158] The control device 14, as explained above, is able to grasp the position (position placed on P, or B, or PAIR), type (the game chip 9 is assigned a different amount of value for each color), and number of the game chip 9 placed by each player 6 by means of the video camera 2, the image analysis device 12, is able to detect which of the guests 6 placed on P (in the case where there are multiple guests 6 placed on P, which of the guests 6 placed the highest amount), and which of the guests 6 placed on B (in the case where there are multiple guests 6 placed on B, which of the guests 6 placed the highest amount). The image analysis device 12 and the control device 14 in the present cheating detection system are configured integrally or in combination with a computer, program, memory composed of a plurality of structures.

[0159] The control device 14 is configured to be able to collate the information on the card face size and color obtained by the image analysis device 12 from the video of each card 1 dealt at the game table 4 (using the video camera 2) and the information on the card face size and color read by the card dealing device 3, and determine whether they are in agreement or disagreement. In accordance with the win / loss result of the game determined by the card dealing device 3 in each game, the control device 14 determines whether the collection of the game chips 9 placed by the losing player (game participant) 6 and the payment of the game chips to the winning player (game participant) 6 are performed correctly in accordance with the win / loss result of the game by analyzing the video of the game progress state by means of the image analysis device 12.

[0160] The control device 14 has the following functions 1) to 5) in accordance with the rules of a certain card game, as the characteristic functions of the present application, to determine whether cheating that violates the rules is performed or not. That is,

[0161] 1) In each game, it is monitored whether there is no change in the game chips 9 during the period from the signal for the start of the card draw obtained from the card dealing device 3, or from the game start operation performed by the dealer 5 pressing the start button 4s, to the display of the win / loss result of the game by the card dealing device 3, using the information obtained by the image analysis device 12 using the video camera 2 (as shown in Figure 8

[0162] 2) After each game, it is monitored whether the loser 6 has taken the game chips 9 without cheating during the period when the dealer 5 collects the game chips 9 placed by the losers among the game participants 6, using the information obtained by the image analysis device 12 using the video camera 2 (as shown in Figure 9

[0163] 3) After each game, it is monitored whether a person other than the dealer 5 (a winner or a loser) has added the won game chips 9W or has placed the game chips 9 again on the winning side without placing them during the period when the dealer 5 collects the game chips 9 placed by the losers among the game participants, using the information obtained by the image analysis device 12 using the video camera 2.

[0164] 4) After each game, it is monitored whether the dealer 5 has placed the paid game chips 9W correctly on the position of the game chips 9 placed by the winners among the game participants 6, using the information obtained by the image analysis device 12 using the video camera 2 (as shown in Figure 10

[0165] 5) After each game (the dealer 5 operates the card dealing device 3 and displays the win / loss result in the display lamp 13), it is monitored whether the winner 6W among the game participants 6 has taken the placed game chips 9 and the paid game chips 9W, using the information obtained by the image analysis device 12 using the video camera 2 (as shown in​​​Figure 11 (As shown).

[0166] The control device 14 analyzes the information obtained by the image analysis device 12 using the camera 2 as follows. That is, by using the analysis results of the image analysis device 12, it detects the movement of the dealer's hand and the game participant's hand, the movement of the game coin, or the movement of the hand and the movement of the game coin, to perform the monitoring of 1) to 5). However, in this basic analysis, it is at least necessary to know who took the game coin 9. The method of this analysis will be described below using Figures 12 to 14.

[0167] Analysis of the situation where dealer 5 takes the game coin 9 placed by game participant 6L (Figure 12).

[0168] The dealer 5 collects the game coins 9 placed by the losing player 6L. This is monitored by analyzing information obtained from the image analysis device 12 using the camera 2 to ensure that the coins are indeed collected. First, image analysis is used to detect whether the placed game coins 9 have been removed from their existing state (…). Figure 12A ) to a state that does not exist ( Figure 12C The changes in ) are then shown. Then, the image of the period during which game coin 9 changes from its present state to its non-present state is presented. Figure 12B ) is analyzed. The graph of the period from the presence of game coin 9 to its absence is analyzed. Figure 12B In the analysis, the hand 5h is determined from which side it extends (from above or outside of Figure 12). If it extends from above (or the hand appears from above and then retracts upwards), the hand 5h is determined to belong to the dealer 5. If the hand extends from any other direction, it is determined to be cheating. Cheating is detected according to this rule.

[0169] During the period when the dealer (5) is recovering the lost coin (9) placed by participant (6L), it is monitored whether other players have taken the lost coin (9) without cheating (Figures 12 and 11). For the image during the period when the coin (9) changes from its present state to its non-present state, as shown... Figure 13 As shown, the analysis of the situation where the loser 6L among the 6 participants in the game was taken was conducted by detecting the hand 6h from the image analysis. Figure 13 If the card extends or moves from below (originally from above), it is considered that the player other than the dealer 5 has taken the game coin 9, and this is considered cheating.

[0170] Analysis of the scenario where the dealer (5) correctly pays (places) 9W of winning game coins, which is then taken by the winner (6W) among the game participants (6). First, regarding... Figure 14A The game coins won, as shown Figure 14BAs shown, repay 90,000 game coins according to the game rules. Detected from Figure 14A The state of the diagram shown Figure 14B The changes in the displayed state are simultaneously analyzed using image analysis to determine if the hand belongs to the dealer (5h). Then, the control device (4), according to the game rules and based on the image analysis results, checks whether the hand is indeed the dealer's hand (5h). Figure 14C As shown, the winner 6W among the 6 participants in the game extends (moves) their hand 6h to the same placement area, after which all 9 game coins disappear. Figure 14D The system can determine whether cheating has occurred by analyzing the state of the data.

[0171] Furthermore, the control device 4 is configured to determine whether the amount of game coins paid by the dealer 5 to the winner 6W among the game participants 6 is correct, based on the amount placed by the winner 6W. A specific example is shown below. Regarding the position and total amount of game coins 9 (which placement area 8 on the P side or B side is game coin 9 placed in), it is conceivable that if game coins 9 are misaligned or overlapped, or if they fall into a blind spot from the position of camera 2, they usually cannot be read. The control device 14 is configured to use a computer or control system based on existing artificial intelligence, a self-learning function based on deep learning (construction) technology, etc., to identify the concealment of game coins 9 due to blind spots (partial concealment of a single game coin, or complete concealment of the game coin), and accurately grasp the position and number of coins. Furthermore, the configuration for detecting the position 8 and type of game coins 9 in the placement area 8 is not limited to this; for example, it can also be configured to detect by reading the ID embedded in the game coin.

[0172] As described above, the control device 14 can use the camera 2 and the image analysis device 12 to determine the position 8 (placement of the game coins 9 placed by each player 6, whether it is placed on P, B, or PAIR), type (the game coins 9 are assigned different values ​​according to each color), and number of coins. It can also detect which player 6 placed the coin on P (if there are multiple players 6 placed on P, the player 6 who placed the highest value), and which player 6 placed the coin on B (if there are multiple players 6 placed on B, the player 6 who placed the highest value).

[0173] Further, the control device 14 of the cheating detection system of the present game analyzes the information obtained by the image analysis device 12 using the camera 2 in accordance with the rules of the card game by the above-mentioned method, and performs monitoring. The monitoring of the above-mentioned 1) to 5) is performed, and it is determined whether or not cheating that violates the rules is not performed. When cheating is detected, the card dispensing detection device 14C causes the abnormality display lamp 16 provided in either one of the card dispensing device 3 or the game table 4 to be lit, and outputs the fact that cheating is detected to the casino management office or the like by wireless or wired transmission 15. Further, a monitor or a lamp that receives the determination result and performs warning or display can be provided in other places.

[0174] As described above, when cheating is detected by the control device 14, a display signal is transmitted to the display lamp 13 or the abnormality display lamp 16 of the card dispensing device 3 at the time point of detection or at an appropriate timing, but in addition to the warning, the function of the card dispensing device 3 to prevent dispensing of the card 1 can be activated after the time point of detection of cheating or error.

[0175] Hereinafter, the card dispensing device 3 used in the table game system of the present application will be described with reference to the drawings. Figures 15 to 19 An embodiment of the card dispensing device 3 used in the table game system of the present application will be described. The card dispensing device 3 includes a card storage portion 102 that stores a plurality of shuffled game cards Is, a card guide portion 105 that guides the shuffled game cards Is when the shuffled game cards Is are manually drawn one by one from the card storage portion 102 by the dealer 5 or the like to the game table 4, an opening portion 106 for taking out the card Is guided by the card guide portion 105, a card detection portion (card detection sensors 22 and 23) that detects that the shuffled game cards Is are drawn when the shuffled game cards Is are drawn, a card reading portion 108 that reads information indicating at least the number (card rank) of the shuffled game cards Is, a control portion 109 that determines the win or loss of the card game in accordance with the number (card rank) of the shuffled game cards Is read one by one by the card reading portion 108, a result display lamp 13 that displays the win or loss result determined by the control portion 109, a dispensing restriction device 30 that is provided in the opening portion 106 and restricts the entry and exit of the card Is to the card storage portion 102, and a management control portion 114 that has the same functions as the control device 14, which are integrated and have the following function: in the case where the control device 14 detects an error or a cheating action of the dealer during the game, the drawing of the card from the card dispensing device 3 is prevented at the time point after the error or the cheating action is detected or at a predetermined timing.

[0176] Next, the card dispensing device 3 used in the table game system of the present application will be described with reference to the drawings. Figure 17 、 16The dispensing restriction device 30 that restricts the entry and exit of the card 1 to the card housing portion 102 will be described. The dispensing restriction device 30 is provided at the card guide 107 of the card guide portion 105 that guides the card 1 taken out one by one from the opening 106 in front of the card housing portion 102 to the game table 4. The dispensing restriction device 30 has a configuration in which when the card 1 passes through the slit 33 between the card guide portion 105 and the card guide 107, the lock member 34 presses the card 1 to prevent the entry and exit of the card 1 in the slit 33. The lock member 34 is moved by the driving portion 35 such as an electromagnetic solenoid or a piezoelectric element, in a manner that can take two states of a position that presses the card 1 (a restriction position) and a passable position that allows the card 1 to pass, as indicated by the arrow m. The driving portion 35 is controlled by the control portion 109 connected directly or indirectly to the control device 14 by wire or wirelessly, to move the lock member 34 between the position that presses the card 1 and the passable position that allows the card 1 to pass. In the control portion 109, the rule of a certain card game is programmed and stored in advance.

[0177] Next, the details of the code reading portion 108 that reads the code 52 indicating the number (rank, face value) of the card 1 from the card 1 when the card 1 is taken out from the card housing portion 102 by hand will be described. Figure 18B A variation of the dispensing restriction device 30 will be described. The dispensing restriction device 40 in the variation has a configuration in which when the card 1 passes through the slit 33 between the card guide portion 105 and the card guide 107 (guide cover), the lock member 36 protrudes into the slit 33 to prevent the movement of the card 1. The lock member 36 is moved by the driving portion 37 such as an electromagnetic solenoid or a piezoelectric element, in a manner that can take two states of a position that prevents the movement of the card 1 (a restriction position) and a passable position that allows the card 1 to pass, as indicated by the arrow m. The driving portion 37 is controlled by the control portion 109 connected to the control device 14, to move the lock member 36 between the position that prevents the movement of the card 1 and the passable position that allows the card 1 to pass.

[0178] Next, the details of the code reading portion 108 that reads the code 52 indicating the number (rank, face value) of the card 1 from the card 1 when the card 1 is taken out from the card housing portion 102 by hand will be described. Figure 17This is a top view of the main components of the card dispensing device 3. In the figure, a code reading unit 108 is provided on the card guide unit 105, which guides manually removed cards 1 one by one from the opening 106 at the front of the card receiving unit 102 onto the game table 4. The card guide unit 105 is an inclined surface, and card guides 107, which also serve as sensor covers, are installed on both sides of its edges. Furthermore, each of the two card guides 107 can be attached and detached using screws or the like (not shown). Removing the card guides 107 exposes the sensor group 115 of the code reading unit 108. The sensor group 115 consists of four sensors: two ultraviolet (UV) sensors 20 and 21, and object detection sensors 22 and 23.

[0179] Object detection sensors 22 and 23 are fiber optic sensors that detect the presence or absence of card 1 and can detect the movement of card 1. Object detection sensor 22 is located upstream of card guide 105 along the moving direction of card 1, and object detection sensor 23 is located downstream. As shown in the figure, the two object detection sensors 22 and 23 sandwich UV sensors 20 and 21 on the upstream and downstream sides. UV sensors 20 and 21 are equipped with an LED (ultraviolet LED) that emits ultraviolet light and a detector. On card 1, the mark M of code 52 is printed using ultraviolet light-emitting ink that emits color when exposed to ultraviolet light. When ultraviolet light (near ultraviolet light) shines on card 1, the detector detects the reflected light of the mark M of code 52 on card 1. UV sensors 20 and 21 are connected to code reading unit 108 and control unit 109 via cables. In code reading unit 108, the combination of marks M is determined based on the output signal of the detector of UV sensors 20 and 21, and the number (card face size) corresponding to each code 52 is determined.

[0180] For the code reading unit 108, the control unit 109 controls the start and end of the reading by the UV sensors 20 and 21 based on the detection signals from the object detection sensors 22 and 23. Furthermore, the control unit 109 also determines whether the card 1 has passed through the card guide unit 105 normally based on the detection signals from the object detection sensors 22 and 23. Figure 19 As shown, quadrilateral markers M, representing the card's face value (number) and suit (hearts or spades, etc.), are arranged in 2 columns and 4 rows along the edge of card 1. If UV sensors 20 and 21 detect marker M, they output an ON signal. In the code reading unit 108, the relative relationship between the two signals input from the two UV sensors 20 and 21 is determined. Therefore, the code reading unit 108 determines the code based on the relative differences between the two markers M detected by the two UV sensors 20 and 21, thus determining the corresponding card 1's face value (number) and suit (type).

[0181] exist Figure 19The relationship between the output of the code 52 and the ON signals of the two UV sensors 20, 21 is shown in the table. According to the comparison result of the relative change of the output of the ON signals of the UV sensors 20, 21, the prescribed combination of the marks M can be determined. As a result, if the combination of the marks M of the two rows is four, and it is printed in four columns, 256 kinds of codes of four to the fourth power can be constituted. The 52 kinds of cards of the game deck are respectively assigned to a certain one of the 256 kinds of codes, and stored as a reference table through a memory or a program, and the code reading section 108 is configured to determine the number (the face size) and the kind (the suit) of the card 1 according to the reference table (not shown) by determining each code 52. In addition, the 256 kinds of codes and the 52 kinds of cards can be corresponded in a freely combined manner, and stored through the reference table, so the combination is complicated, and the combination of the 256 kinds of codes and the 52 kinds of cards can be changed by time and place. It is preferable to print the code with paint that can be visualized by accepting ultraviolet light, and print it at a position that does not coincide with the kind notation and the index 103 of the card.

[0182] Also, in the above-described embodiment, the image analysis device 12 and the control device 14 are devices having an artificial intelligence effective utilization type or a deep learning configuration, but the image analysis device 12 and the control device 14 specifically can perform analysis of an image and the above-described various controls using a Scale-Invariant Feature Transform (SIFT) algorithm, a Convolutional Neutral Network (CNN), deep learning, machine learning, or the like. These technologies are technologies for recognizing an object contained in an image by image recognition of an image, and in particular, in recent years, a deep learning technology in which a neural network is made multilayered is used to recognize an object with high accuracy. This deep learning technology generally recognizes an object with high accuracy by overlapping layers across multiple stages in an intermediate layer between an input layer and an output layer of a neural network. In this deep learning technology, in particular, a convolutional neural network has higher performance than recognizing an object based on an existing image feature amount, and thus is attracting attention.

[0183] In the convolutional neural network, a recognition object image with a label is learned, and a main object contained in the recognition object image is recognized. When there are multiple main objects in the learning image, the main objects are specified with a region rectangle, and the image corresponding to the specified region is learned with a label. Furthermore, in the convolutional neural network, it is also possible to determine the main object in the image and the position of the object.

[0184] If the convolutional neural network is further described, in the recognition flow of the object, by performing edge extraction processing and the like on the recognized object image, a candidate region is extracted based on the local feature, and the candidate region is input to the convolutional neural network, and based on the extracted feature vector, classification is performed, and the highest confidence candidate region classified is obtained as the recognition result. The so-called confidence is a quantity indicating how relatively high the similarity of a certain image region and the subject of the image learned together with the label is compared with other levels.

[0185] Further, regarding the device having an artificial intelligence effective utilization type or a deep learning configuration, it is described in U.S. Patent No. 9361577, U.S. Patent Publication No. 2016-171336, U.S. Publication No. 2015-036920, Japanese Patent Publication No. 2016-110232, and the like, which are incorporated into the present specification by reference.

[0186] The above describes various embodiments of the present application, but the above embodiments can of course be modified by those skilled in the art within the scope of the present application, and the device of the present embodiment can be appropriately modified according to the needs in the game to which it is applied.

[0187] Explanation of symbols

[0188] 1 game card

[0189] 1s multiple shuffled game cards

[0190] 2 surveillance camera

[0191] 3 card dispensing device

[0192] 4 game table

[0193] 5 dealer

[0194] 6 guest (game participant / player)

[0195] 7 chair

[0196] 8 placement area

[0197] 9 game chip

[0198] 10 area

[0199] 10P P area

[0200] 10B B area

[0201] 11 game record device

[0202] 12 image analysis device

[0203] 13 result display lamp

[0204] 14 control device

[0205] 14C card dispensing detection device

[0206] 15 output (abnormality determination result, etc.)

[0207] 16 abnormality display lamp

[0208] 30 dispensing restriction device

[0209] 33 slit

[0210] 34 lock member

[0211] 35 drive section

[0212] 36 lock member

[0213] 37 drive section

[0214] 40 dispensing restriction device

[0215] 102 card accommodating section

[0216] 103 index

[0217] 105 card guide section

[0218] 106 opening section

[0219] 107 card guide

[0220] 109 control section

[0221] 112 side monitor

Claims

1. A system which is a system in a casino, and is provided with: a game table having a plurality of placement areas including a player area and a dealer area for placement of gaming chips; a chip tray provided to the game table, which stores all the gaming chips owned by the casino; a camera which takes images of the plurality of placement areas and the gaming chips placed in any of the plurality of placement areas from an oblique upper direction, and generates images including the gaming chips; an image analysis device which performs image analysis using a deep learning technique on the images, thereby recognizing respective kinds of the gaming chips, and in which placement area of the plurality of placement areas each of the gaming chips is placed; a game result determination device which determines a game result of each game of a card game performed on the game table; and a control device which calculates a collection amount of the gaming chips and / or a payout amount of the gaming chips based on both a result of the image analysis by the image analysis device and a determination result by the game result determination device, the camera is disposed in a manner that an optical axis thereof is inclined with respect to a table surface of the game table, so as to take images of the plurality of placement areas in which positions, kinds, and numbers of the gaming chips placed by respective players can be recognized, the control device determines whether or not there is a difference between an expected number of the gaming chips in the chip tray after collection based on the calculated collection amount and an actual number of the gaming chips in the chip tray after collection, an expected number of the gaming chips in the chip tray after payout based on the calculated payout amount and a number of the gaming chips before payout, and / or an expected number of the gaming chips in the chip tray after payout based on the calculated collection amount, the calculated payout amount, and a number of the gaming chips before collection, and an actual number of the gaming chips in the chip tray after payout, thereby determining whether or not there is a difference between the expected number and the actual number, the control device further has a function of determining a change in the gaming chips in at least one of the following cases by detecting a change in hands of a dealer and game participants, or the change in the hands and a change in the gaming chips, using a result of analysis by the image analysis device, and determining that there is a cheating in a case where there is a change in the gaming chips in any of the following cases: 1) whether or not there is no change in the gaming chips during a period from a start of card drawing or from a game start operation of the dealer to a display of a win or loss result of a game by a card distribution device in each game, 2) whether or not a loser among the game participants does not take the gaming chips after each game, during a period in which the dealer collects the gaming chips placed by the loser, and 3) whether or not the gaming chips are added after each game, during a period in which the dealer collects the gaming chips placed by the loser.

2. The system according to claim 1, wherein ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ The camera is configured to take an image of at least one plane of the chips placed on the game table.

3. The system according to claim 1, wherein The system is provided with a plurality of the cameras including a first camera and a second camera, the first camera and the second camera at least partially taking an image of the same placement area.

4. The system according to claim 1, wherein Each of the chips is provided with an RFID tag storing information on the amount of the chip, The system is further provided with an RFID antenna configured to read the RFID tag of the chip housed in the chip tray and determine the amount of the chip housed in the chip tray.

5. The system according to any one of claims 1 to 4, wherein The game result determination device is a card distribution device configured to distribute cards on the game table.

6. The system according to claim 1, wherein Further provided is a game recording device configured to index or time the image or capable of determining and reproducing the chip collection scene or the payout scene.

7. The system according to claim 4, wherein The chip tray is provided with a chip tray for collection configured to collect and temporarily store the chips placed by the losing player, The control device Based on the result of the image analysis by the image analysis device, the kind and the number of the chips placed by each player in each of the placement areas are recognized, It is determined whether there is a difference between the calculated collection amount and the actual total amount of the chips in the chip tray for collection after the chips placed by the losing player are collected.

8. The system according to claim 7, wherein The actual total amount of the chips in the chip tray after the collection and the payout is obtained at any one of the following timings: 1) when the payout of the winning chips is completed; 2) when the cards used in the game are collected and discarded in the discard area of the table; 3) when a prescribed button attached to the win / loss result determination device is pressed; and 4) when the sign indicating the win / loss is restored.

9. The system according to claim 1, wherein The control device is configured to 1) grasp the position, the kind and the number of the chips placed on each of the game positions of the game table, compare the win / loss history of each player obtained from the win / loss result of each game and the amount of the chips obtained with the past game statistical data, and extract a condition in which there is an abnormality as an abnormal condition, and 2) compare the condition in which the amount of the chips placed on the game position of the game table when losing is less than the amount of the chips placed when winning with the past game statistical data, and extract a condition in which there is an abnormality as an abnormal condition.

10. The system according to claim 1, wherein The control device can compare and determine whether the amount of chips held in the chip tray of the dealer of the game table is reduced based on the payout amount of chips corresponding to the paper money used for the purchase or the payout amount of paper money corresponding to the purchased chips after the purchase of chips with paper money.

11. The system according to claim 10, wherein, The control device further has a database in which purchase histories of chips purchased with paper money are recorded, and can compare and determine whether the amount of chips held in the chip tray of the game table is reduced based on the total of the payout amount of chips corresponding to the paper money used for the purchase or the payout amount of paper money corresponding to the purchased chips with reference to the database in a certain time or in a day.

12. The system according to claim 9, wherein, The control device can determine the presence of the difference or determine the player who extracted the abnormal playing position by means of the image analysis device.

13. The system according to claim 12, wherein, The control device has a warning function of notifying the presence of the determined player to another game table when the determined player leaves the seat and sits at the other game table.

Images