Management system

Abstract

To provide a novel system for detecting fraud in a game in a game parlor or a mistake and fraud when betting chips and settling an amount.SOLUTION: A fraud detection system which detects fraud in a game of performing collection and redemption of chips in accordance with a win or lose result includes: a camera 2 which captures an image of chips 9 contained in a chip tray 17 of a dealer 5; an image analyzing apparatus 12 which analyses the image captured by the camera 2 to detect an amount of the chips 9 contained in the chip tray 17; a card distribution device 13 which determines a win or lose result of a game; and a control device 14 which compares the win or lose result of the game with an amount of the chips 9 contained in the chip tray 17 before and after collection and redemption of the chips to detect fraud.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a system for detecting fraud in games at a gaming establishment, or mistakes and fraud during chip betting or settlement.

Background Art

[0002] At gaming establishments such as casinos, attempts are being made to prevent various types of fraud. Gaming establishments are equipped with surveillance cameras for monitoring fraud, and they prevent fraud by determining fraud in games and fraud through chip collection or reimbursement different from the winning or losing results from the images obtained from the surveillance cameras.

[0003] On the other hand, it has been proposed to attach a wireless IC (RFID) tag to each chip in order to grasp the number and total amount of the wagered chips.

[0004] In the card game monitoring system described in Patent Document 1, it is determined whether the chips placed on the gaming table are collected or reimbursed as per the winning or losing results by analyzing the movement of the chips through image analysis, and monitoring of fraud is performed.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] An object of the present invention is to provide a novel system for detecting fraud in games at a gaming establishment, or mistakes and fraud during chip betting or settlement.

Means for Solving the Problems

[0007] A fraud detection system according to an aspect of the present invention is a fraud detection system in a casino having a plurality of gaming tables, including a game recording device that records, as video, the state of a game played on the gaming table by a camera, an image analysis device that analyzes the video of the recorded game state, a win / loss result determination device that determines the win / loss result of each game on the gaming table, and a control device that detects fraud committed on the gaming table using the image analysis result by the image analysis device and the win / loss result determined by the win / loss result determination device. The control device grasps the position, type, and number of chips wagered by each player via the image analysis device, and grasps the total amount of chips in the dealer's chip tray on the gaming table. From the total amount of chips in the chip tray before the settlement of each game, the increase or decrease amount of chips in the game is added or subtracted based on the position, type, and number of chips wagered by all players in the game and the win / loss result of the game obtained by the win / loss result determination device. Then, the control device compares the total amount of chips that should be in the chip tray after the 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 via the image analysis device, and determines whether there is a difference between the total amount that should be and the actual total amount.

[0008] In the above fraud detection system, the control device grasps the position, type, and number of chips wagered by each player via the image analysis device. When all the losing chips wagered by each player have been collected, the control device grasps the actual total amount of chips in the chip tray. From the total amount of chips in the chip tray before the settlement of each game, the control device adds the increase amount of the chip tray in the game based on the position, type, and number of chips wagered by the losing player to obtain the total amount of chips that should be in the chip tray in the game, and compares it with the actual total amount of chips in the chip tray. Then, the control device determines whether there is a difference between the total amount that should be and the actual total amount.

[0009] In the above-mentioned fraud detection system, the control device subtracts, from the total amount of chips in the chip tray before the settlement of each game, the increase in the chip tray in the game obtained by adding the positions, types, and numbers of the chips wagered by the losing player, to obtain the total amount of chips that should be in the chip tray. The control device then compares this with the actual total amount of chips in the chip tray. If it is determined that there is no difference between the total amount that should be and the actual total amount, and if it is determined that there is a difference between the total amount that should be in the chip tray after settlement at the end of the game and the actual total amount of chips in the chip tray obtained via the image analysis device at the end of the game, then it is determined that there is an error in the payment, and a payment error signal may be generated to notify of the payment error.

[0010] In the above-mentioned fraud detection system, the chip tray is provided with a recovered chip tray for recovering and temporarily storing the chips wagered by the losing player. The image analysis device and the control device compare the amount of chips that should be in the recovered chip tray calculated from the positions, types, and numbers of the chips wagered by the losing player with the actual total amount of chips in the recovered chip tray, and determine whether there is a difference between the total amount that should be and the actual total amount in the recovered chip tray.

[0011] In the above-mentioned fraud detection system, obtaining the actual total amount of chips in the chip tray after settlement at the end of the game via the image analysis device may be any of the following: 1) When the repayment for 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 predetermined button attached to the win / loss result determination device is pressed; 4) When the marker indicating the win / loss is reset.

[0012] In the above-mentioned fraud detection system, when the control device determines a difference in that the actual total amount of chips grasped in the dealer's chip tray on the gaming table does not correspond to the increase or decrease amount of chips calculated from the chip amounts wagered by all players and the win / loss result of the game, the game recording device may be configured to assign an index or time to the acquired video, or to identify and reproduce a chip collection scene or a payment scene so that the recording of the game in which the difference occurred can be analyzed.

[0013] In the above-mentioned fraud detection system, the image analysis device or the control device may have a structure that enables it to obtain information on the types, numbers, and positions of wagered chips even when some or all of the plurality of chips placed on the gaming table are hidden due to the blind spot of the camera.

[0014] In the above-mentioned fraud detection system, the control device 1) grasps the position, type, and number of chips wagered at each play position on the gaming table, and compares the win / loss history of each player obtained from the win / loss result of each game and the amount of chips obtained with the statistical data of past games to extract it as an abnormal situation, or 2) at the play position on the gaming table, extracts as an abnormal situation a state where the amount of wagered chips when losing is less than the amount of wagered chips when winning, compared with the statistical data of past games. It may have a structure that enables this.

[0015] In the above-mentioned fraud detection system, the control device may be able to compare and determine whether the amount of chips grasped in the dealer's chip tray on the gaming table has increased or decreased according to the payment amount of chips corresponding to the exchanged bills or the payment amount of bills corresponding to the exchanged chips after the exchange of bills and chips.

[0016] In the above-mentioned fraud detection system, the control device further includes a database that records the history of bill and chip exchanges. At regular intervals or on a daily basis, the database is referenced to determine whether the amount of chips grasped in the dealer's chip tray on the gaming table has increased or decreased according to the total amount of chip payments corresponding to the exchanged bills or the total amount of bill payments corresponding to the exchanged chips.

[0017] In the above-mentioned fraud detection system, the control device may be able to identify the player at the play position extracted as the difference or special situation via the image analysis device.

[0018] In the above-mentioned fraud detection system, when the identified player leaves the seat and arrives at another gaming table, the control device may have a warning function to notify the presence of the specific player at the other gaming table.

[0019] In the above-mentioned fraud detection system, the control device further 1) In each game, whether there is any movement of chips after the card draw is started or before the game result is displayed by the card distribution device after the dealer's game start operation. 2) After each game, whether the loser among the game participants is not taking chips while the dealer is collecting the chips wagered by the loser. 3) After each game, whether additional chips are added while the dealer is collecting the chips wagered by the loser among the game participants. 4) After each game, whether payment is made to the position of the chips wagered by the winner among the game participants. 5) After each game, whether the winner among the game participants takes the wagered chips and the paid chips. and may be equipped with a function to determine at least one of the above.

[0020] In the above-described fraud detection system, the win / loss result determination device may be a card distribution device that distributes cards on the gaming table, or a control device that determines the win / loss results of each game from the information of the image analysis device that reads the cards distributed on the gaming table with a camera.

Advantages of the Invention

[0021] According to the fraud detection system of the present invention, fraud in the collection and repayment of chips according to the win / loss results of the game can be detected.

[0022] Further, according to the system of the present invention, even if the card is bent due to the squeezing of the card by the player, which is often performed in baccarat games and the like, the rank and suit of the card can be determined by image analysis, and the total amount of the dead corners and overlapping chips can be grasped together with the position. In addition, fraud at the time of exchanging bills and chips can also be detected.

Brief Description of the Drawings

[0023]

Figure 1

Figure 2A

Figure 2B

Figure 3A

Figure 3B

Figure 4

Figure 5A

Figure 5B

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12A

Figure 12B

Figure 12C

Figure 13

Figure 14A

Figure 14B

Figure 14C

Figure 14D

Figure 15

Figure 16

Figure 17

Figure 18A

Figure 18B

Figure 19

MODE FOR CARRYING OUT THE INVENTION

[0024] (First Embodiment) In gaming venues such as casinos, chips are stacked up and placed on the gaming table. However, there is a problem that the total amount cannot be accurately read by the IC tag reader installed under the gaming table. If the sensitivity of the reader is increased, chips placed at different positions (where the outcome depends on the position) will be added up, and the total amount of chips for each position cannot be grasped. In addition, in imaging from a camera, there are problems such as blind spots due to the viewing angle of the camera or the total amount of chips cannot be grasped because they are in the shadow due to overlapping.

[0025] Also, although it is often done in baccarat games, there is a problem that the cards are bent due to actions such as squeezing the cards by the player (the act of bending the face-down cards and gradually looking at the rank etc. of the cards while enjoying), and the rank and suit of the cards cannot be determined by image analysis from the camera.

[0026] Furthermore, cheating in the gaming table has become more sophisticated. New problems have been identified, such as cheating using advanced betting methods that cannot be detected by simply detecting a large amount of winnings at the gaming table, and cheating that cannot be detected by cameras or tracking of winnings. In addition, the prior art is not sufficient to prevent illegal acts resulting from collusion between dealers and players.

[0027] To solve the above various problems, the fraud detection system in a gaming venue having a plurality of gaming tables according to the first embodiment is as follows: A fraud detection system in a gaming venue having a plurality of gaming tables, A game recording device that records the progress state of the game played on the gaming table as a video via a camera including dealers and players, An image analysis device that analyzes the video of the recorded game progress state, A card distribution device that determines and displays the winning or losing result of each game on the gaming table, A control device that detects fraud committed on the gaming table using the image analysis result by the image analysis device and the winning or losing result determined by the card distribution device.

[0028] Furthermore, there is a fraud detection system. The card dispensing device has a structure capable of reading the rank of the cards to be dispensed. The control device collates the rank information obtained by the image analysis device from the images of each card distributed on the gaming table with the rank information of the cards read by the card dispensing device to determine whether they match or not.

[0029] Furthermore, there is a fraud detection system. The image analysis device or the control device has an artificial intelligence utilization type or deep learning structure capable of obtaining the rank information of a card from a card that has been bent or soiled by a player on the gaming table.

[0030] Furthermore, there is a fraud detection system. The control device grasps the position, type, and number of chips wagered by each player via the image analysis device, and determines whether the collection of losing chips wagered by each player and the payment to winning chips are appropriately made according to the winning or losing result of the game by analyzing the video of the progress of the game via the image analysis device.

[0031] Furthermore, there is a fraud detection system. The image analysis device or the control device has an artificial intelligence utilization type or deep learning structure capable of obtaining the information on the type, number, and position of the wagered chips even when some or the whole of the plurality of chips placed on the gaming table are hidden due to the blind spot of the camera.

[0032] Furthermore, there is a fraud detection system. The control device has an artificial intelligence utilization type or deep learning structure capable of comparing and calculating whether the amount of chips grasped in the dealer's chip tray on the gaming table has increased or decreased according to the collection of losing chips wagered by each player and the payment amount to winning chips after the game ends and is settled.

[0033] Furthermore, there is a fraud detection system in which a control device grasps the position and amount of chips wagered at each play position on a gaming table, and compares the win / loss history of each player obtained from the win / loss results of each game and the amount of chips obtained with the statistical data of past games to extract as a special situation, which is an artificial intelligence utilization type or deep learning structure.

[0034] Furthermore, there is a fraud detection system in which a control device, at a play position on a certain gaming table, is an artificial intelligence utilization type or deep learning structure capable of extracting, as a special situation compared with the statistical data of past games, a state where the amount of chips wagered when losing is less than the amount of chips wagered when winning.

[0035] Furthermore, there is a fraud detection system in which a control device has a structure capable of identifying an individual player at a play position where a special situation is extracted via the image analysis device or a player who has won a certain amount or more.

[0036] Furthermore, there is a fraud detection system in which a control device has a warning function that notifies the existence of the specific player at another gaming table when the specific player leaves and arrives at another gaming table.

[0037] To solve the above various problems, a fraud detection system in a casino having a plurality of gaming tables according to the present invention includes a game recording device that records, as video via a camera including a dealer and players, the progress state of a game played on the gaming table; a card distribution device that determines and displays the win / loss results of each game on the gaming table; an image analysis device that analyzes the video of the recorded game progress state; a control device that can detect bills and chips on the gaming table using the image analysis result by the image analysis device. The image analysis device or control device can detect that the exchange of bills and chips is being carried out on the gaming table in situations other than during card dealing, based on the information obtained from the card distribution device or the dealer. Further, it can recognize the total amount of genuine bills verified by a black light. Additionally, even when a plurality of chips placed on the gaming table as exchange targets are partially or entirely hidden due to the blind spot of the camera, it can recognize the total amount of the chips. It compares the total amount of bills issued by the player on the gaming table with the total amount of chips issued by the dealer and can determine whether the amounts of both match. It has an artificial intelligence utilization type or deep learning structure.

[0038] Furthermore, there is a fraud detection system. The control device has an artificial intelligence utilization type or deep learning structure that can perform a comparison calculation to determine whether the amount of chips grasped in the dealer's chip tray on the gaming table has increased or decreased according to the payment amount of chips corresponding to the exchanged bills after the exchange of bills and chips has been carried out and settled.

[0039] Furthermore, there is a fraud detection system. The control device has an artificial intelligence utilization type or deep learning structure that can perform a comparison calculation of the coincidence or non - coincidence between the deposit amount of bills by the input of the dealer after the exchange of bills and chips has been carried out and settled and the total amount of bills based on the image analysis result by the image analysis device. Additionally, further, the control device has an artificial intelligence utilization type or deep learning structure that can perform a comparison calculation of the coincidence or non - coincidence between the total deposit amount of bills by the input of the dealer on the gaming table handled by the dealer and the total amount of bills based on the image analysis result by the image analysis device.

[0040] According to the fraud detection system of the present embodiment, even if a card is bent due to a player squeezing the card, which often occurs in baccarat games and the like, the rank and suit of the card can be determined by image analysis, and the total amount, along with the position, of blind spots and overlapping chips can be grasped. Also, fraud during the exchange of bills and chips can be detected.

[0041] The overall outline of the fraud detection system in a casino having a plurality of gaming tables according to the first embodiment of the present invention will be further described in more detail below. FIG. 1 is a diagram showing the overall outline of the system. The fraud detection system in a casino having a plurality of gaming tables 4 includes a game recording device 11 that records the progress state of the game played on the gaming table 4 as video via a plurality of cameras 2 including the player 6 and the dealer 5, and an image analysis device 12 that analyzes the image of the recorded progress state of the game. Further, it is provided with a card distribution device 3 that determines and displays the winning or losing result of each game on the gaming table 4. The card distribution device 3 is a so-called electronic shoe already used by those skilled in the art, and the rules of the game are programmed in advance, and it has a structure capable of reading the information of the distributed card C and determining the winning or losing of the game. For example, in the baccarat game, the win of the banker, the win of the player, and a tie (draw) are basically determined by the ranks of 2-3 cards, and the determination result (winning or losing result) is displayed on the result display lamp 13.

[0042] This fraud detection system further compares the actual rank of the card based on the image analysis result by the image analysis device 12 with the winning or losing result determined by the card distribution device 3, and includes a control device 14 that detects fraud (such as a mismatch between the total rank of the distributed cards and the winning or losing result) performed on the gaming table 4. The card distribution device 3 has a structure capable of reading the rank (A, 2-10, J, Q, K) and suit (hearts, spades, etc.) of the card C manually distributed by the dealer 5. The control device 14 collates the rank and suit information obtained by the image analysis device 12 (using artificial intelligence) from the video of each card distributed on the gaming table 4 (captured using the camera 2) with the rank and suit information of the card read by the card distribution device 3 to determine whether they match or not. The image analysis device 12 and the control device 14 in this fraud detection system have a structure that comprehensively includes a computer, a program, and a memory composed of an integrated or multiple configurations.

[0043] The image analysis device 12 and the control device 14 have an artificial intelligence-utilizing or deep learning structure that can obtain information on the rank of a card even if the card C is distributed on the gaming table 4 and is bent or soiled by the player 6. As shown in FIG. 4, for a soiled card C, a situation where it is difficult to distinguish between clubs and spades may occur. Even in such a case, by analyzing and determining the image using an artificial intelligence-utilizing computer or control system or deep learning (structure) technology, it becomes possible to distinguish the suit. Also, even if the card is bent due to card squeezing by the player, which is often done in baccarat games and the like, by utilizing self-learning of a large number of image deformation examples, etc., an artificial intelligence-utilizing computer or control system or deep learning (structure) technology can recognize the suit and rank that the card had before deformation. Since an artificial intelligence-utilizing computer or control system or deep learning (structure) technology is already known and available to those skilled in the art, detailed description thereof will be omitted.

[0044] The control device 14 having an artificial intelligence-utilizing type or deep learning structure can grasp at which position (player, banker, or pair) in the betting area 8 each player 6 bets the chip 9 via the camera 2 and the image analysis device 12, the type of the bet chip 9 (the chip 9 has different face values assigned for each color), and the number of chips. The chips 9 are stacked shifted as shown in FIG. 2A rather than being stacked aligned vertically. In this case, when the camera 2 is positioned in the direction of arrow X shown in FIG. 2A (or when the orientation of the chip 9 becomes a blind spot relatively), it is assumed that the chip 9 cannot be seen (enters the blind spot) as shown in FIG. 2B. In the artificial intelligence-utilizing computer or control system and deep learning (structure) technology, the self-learning function or the like is used to recognize the hiding due to the blind spot of the chip 9 (when a part of a single chip is hidden or when the entire chip is hidden), and the number of chips is accurately grasped. Thus, since it is possible to grasp at which position (player, banker, or pair) in the betting area 8 the chip 9 is bet, the type of the bet chip 9 (the chip 9 has different face values assigned for each color), and the number of chips, the control device 14 determines whether or not the collection of the losing chips bet by each player 6 (shown by arrow L) and the payment to the winning player 6W of the winning chips (9W) are properly made according to the winning or losing result of the game determined by the card distribution device 3 in each game by analyzing the video of the progress state of the game via the image analysis device 12.

[0045] The control device 14 can analyze and grasp the total amount of chips 9 in the chip tray 17 of the dealer 5 on the gaming table 4 using the image analysis device 12. After the game ends and is settled, according to the recovery of the losing chips 9 wagered by each player 6 and the amount of payment 9W to the winning player 6W in winning chips, it is possible to compare and calculate whether the total amount of chips 9 in the chip tray 17 has increased or decreased according to the win-lose result of the game. Even if the total amount of chips 9 in the chip tray 17 is always grasped by means such as RFID, whether the increase or decrease amount is correct or not is determined by the control device 14 analyzing the video of the game progress state via the image analysis device 12. These also utilize an artificial intelligence utilization type or a deep learning structure.

[0046] In this example, based on the win-lose result of the game, information on which type of chips 9 were wagered, how many were wagered at which position (player, banker, pair) in the wagering area 8, and the increase or decrease amount of chips 9 in the chip tray 17 after the recovery of the losing chips and the repayment for the winning chips 9, fraud and mistakes are detected. Therefore, even without knowing the movement of chips 9 after the game ends, that is, whether the wagered chips 9 have moved to the player side or the dealer side, fraud and mistakes can be detected.

[0047] Here, for example, in the case of baccarat, the win-lose result of the game can be determined according to the baccarat rules by reading the rank of the cards C dealt in that game in the card dealing device 3. Also, the win-lose result of the game can be determined by photographing the gaming table 4 with the camera 2, analyzing the image with the image analysis device 12, and comparing the analysis result with the game rules by the control device 14. In this case, the camera 2, the image analysis device 12, and the control device 14 constitute a win-lose result determination device. Information on which player is at each play position 7 and which type of chips 9 were wagered, how many were wagered at which position (player, banker, pair) in the wagering area 8 can be obtained by photographing the chips 9 placed in the wagering area 8 with the camera 2 and analyzing the image for each play position 7 with the image analysis device 12.

[0048] In addition, the increase or decrease amount of the chips 9 in the chip tray 17 before and after the collection of the losing chips 9 and the repayment for the winning chips 9 can be calculated by comparing the total amount of the chips 9 in the chip tray 17 before the collection of the losing chips 9 and the repayment for the winning chips 9 with the total amount of the chips 9 in the chip tray 17 after the collection of the losing chips 9 and the repayment for the winning chips 9. The total amount of the chips 9 in the chip tray 17 before the collection of the losing chips 9 and the repayment for the winning chips 9, and the total amount of the chips 9 in the chip tray 17 after the collection of the losing chips 9 and the repayment for the winning chips 9 can be detected by photographing the chip tray 17 containing the chips 9 with the camera 2 and analyzing the image with the image analysis device 12. Further, by embedding an RFID indicating the amount therein in the chip 9 and providing an RFID reader in the chip tray 17, the total amount of the chips 9 accommodated in the chip tray 17 may be detected.

[0049] For example, assume that the total amount of the chips 9 in the chip tray 17 before the start of the game is Bb, and the total amount of the chips 9 in the chip tray 17 after the game ends and the collection of the losing chips and the repayment for the winning chips are completed is Ba. Also, in this game, assume that the total amount of all the play positions 7 of the chips 9 wagered in the player area is bp, the total amount of all the play positions 7 of the chips 9 wagered in the banker area is bb, and the total amount of all the play positions 7 of the chips 9 wagered in the tie area is bt. For example, when the winning or losing result of this game is the banker's win, Ba - Bb = bp - bb + bt should hold. Alternatively, the total amount Ba of the chips 9 in the chip tray 17 after the game ends should be (Bb + bp - bb + bt). If it is not the case, it can be determined that there is an irregularity or a mistake in the collection or repayment of the chips.

[0050] FIG. 3A is a diagram showing details of the chip tray according to the present embodiment, and FIG. 3B is a diagram showing another example of the chip tray. The chip tray 17 is provided with a recovery chip tray 171 for recovering and temporarily storing the chips 9L wagered by the losing player 6L, and a repayment chip tray 172 for storing the chips 9W to be repaid. The image analysis device 12 and the control device 14 grasp the position, type, and number of the chips 9L wagered by the losing player 6L, and calculate the increased amount of the chips 0L in the game (the amount that should be of the chips 9 in the recovery chip tray 171). Further, the image analysis device 12 and the control device 14 grasp the actual total amount of the chips 9 in the recovery chip tray 171 after the recovery, and compare the should-be total amount with the actual total amount to determine whether there is a difference.

[0051] Also, for the repayment of the chips 9W to the winning player 6W, by using the chips 9 in the repayment chip tray 172, sufficient time can be secured for the image analysis device 12 and the control device 14 to grasp the actual total amount of the chips 9 in the recovery chip tray 171 after the recovery.

[0052] The gaming table 4 includes a discard area 41 and / or a discard slot 42 for discarding the cards C used in the game. Each time the game ends, the cards C used in the game are collected and placed in the discard area 41 or the discard slot 42 on the gaming table 4 and discarded.

[0053] The gaming table 4 further includes a marker 43 indicating the win or loss of the game. FIG. 5A is a plan view showing the front of the marker, and FIG. 5B is a plan view showing the back of the marker. In the baccarat game, two types of markers are used: a marker 43a indicating the player's win and a marker 43b indicating the banker's win. When the result of the game comes out, the dealer 5 turns over the marker of the winning party among the player or the banker. Thereby, the win or loss of the game is clearly shown on the table. The turned-over marker is returned to its original state by the dealer 5 after the recovery and repayment of the chips 9 are completed. Returning the marker to its original state also means that the next game can be started.

[0054] As described above, in this embodiment, the control device 14 calculates the chip balance based on the amount of bet chips on the gaming table 4 and the win / loss result for each game, and verifies an increase in the remaining amount of chips in the chip tray 17 after the game. If a difference is detected in this verification, the control device 14 issues an alarm or adds a record to that effect to the recording of the video captured by the camera 2. The casino operator can investigate the cause of the difference by checking the video.

[0055] The fraud detection system of this embodiment adds and subtracts the increase or decrease amount of chips in the game calculated from the position, type, and number of chips 9 bet by all players 6 in the game and the win / loss result of the game obtained by the win / loss result determination device from the total amount of chips 9 in the chip tray 17 before the settlement of each game, and compares the supposed total amount of chips 9 in the chip tray 17 after the settlement at the end of the game with the actual total amount of chips 9 in the chip tray 17 at the end of the game obtained via the image analysis device 12, and determines whether there is a difference between the supposed total amount and the actual total amount.

[0056] The control device 14 grasps the position, type, and number of chips bet by each player via the image analysis device 12, and when all the losing chips bet by each player have been collected, grasps the actual total amount of chips in the chip tray, and compares the supposed total amount of chips 9 in the chip tray 17 obtained by adding the increase amount of the chip tray 17 in the game from the position, type, and number of chips bet by the losing player to the total amount of chips in the chip tray before the settlement of each game with the actual total amount of chips 9 in the chip tray 17, and determines whether there is a difference between the supposed total amount and the actual total amount.

[0057] The control device 14 compares the total amount of chips 9 in the chip tray 17 before the settlement of each game with the total amount of chips 9 that should be in the chip tray 17 in that game, which is obtained by adding the increase in the chip tray 17 in that game based on the position, type, and number of chips 9 wagered by the losing player, and the actual total amount of chips 9 in the chip tray 17. If it is determined that there is no difference between the total amount that should be and the actual total amount, and when comparing the total amount that should be in the chip tray 17 after settlement at the end of the game with the actual total amount of chips 9 in the chip tray 17 obtained via the image analysis device 12, if it is determined that there is a difference between the total amount that should be and the actual total amount, it is determined that there is an error in the payment, and a payment error signal is generated to notify the error in the payment.

[0058] The chip tray 17 is provided with a collected chip tray 171 for collecting and temporarily storing the chips 9 wagered by the losing player. The image analysis device 12 compares the total amount of chips 9 that should be in the collected chip tray 171, which is calculated by adding the increase in the chips 9 in that game based on the position, type, and number of chips 9L wagered by the losing player, with the actual total amount of chips 9 in the collected chip tray 171, and determines whether there is a difference between the total amount that should be and the actual total amount.

[0059] When the control device 14 determines that there is a difference that the actual total amount of the chips 9 grasped in the chip tray 17 of the dealer 5 of the gaming table 4 does not correspond to the increase or decrease amount of the chips calculated from the total amount of chips wagered by all players and the winning or losing result of that game, the game recording device 11 assigns an index or time to the acquired video, or specifies and can play back the chip collection scene or payment scene so that the recording of the game in which the above difference occurred can be analyzed in the game recording device 11.

[0060] In this way, the control device 14 obtains the total amount of chips in the chip tray 17 after settlement at the end of the game via the image analysis device 12. In this case, the post - settlement judgment is assumed to occur when any of the following 1) to 4) occurs. 1) When the repayment for the winning chip 9 is completed, 2) When the card C used in the game is collected and discarded in the discard area 41 or the discard slot 42 of the table, 3) When a predetermined button attached to the win / loss result determination device is pressed, 4) When the marker 43 indicating win / loss is reset.

[0061] In addition, the control device 14 grasps the position (the position bet on the player, banker, or pair) and the amount (type and number of chips) of the chips bet at each play position 7 of the game table 4, and compares the win / loss history of each player 6 obtained from the win / loss results of each game and the amount of chips obtained (the amount won) with the statistical data of a large number (big data) of past games to extract as a special situation (set by the casino) in an artificial intelligence utilization type or deep learning structure. Typically, the occurrence of a winning amount of a certain amount (one million dollars) or more, or at a play position 7 of a certain game table 4, where the amount of chips bet when losing is small and the amount of chips bet when winning is large continues for several games, and this can be extracted as a special situation compared with the statistical data (big data, etc.) of past games. It is equipped with a control device 14 of an artificial intelligence utilization type or deep learning structure.

[0062] Furthermore, the control device 14 of this fraud detection system is (integrated with the image analysis device 12) structured to be able to identify an individual player 6 at a play position 7 where a special situation is extracted or a win of a certain amount or more is achieved. Such identification of the player 6 is obtained in the image analysis device 12 by extracting feature points from the face image and attaching an identity number (ID, etc.) for identification. And when the identified player 6 leaves and arrives at another game table, the control device 14 has a warning function to notify the existence of the specific player at the other game table. Specifically, it notifies the pit manager who manages each game table 4 and each table responsible person (it may be a dealer) to prevent further special phenomena.

[0063] The control device 14 further includes a database that stores the history of the exchange between the bills K and the chips 9. It refers to the database at regular intervals or on a daily basis, and compares and determines whether the amount of the chips 9 grasped in the chip tray 17 of the dealer 5 on the gaming table 4 has increased or decreased according to the total amount of the chips 9 paid corresponding to the exchanged bills K or the total amount of the bills K paid corresponding to the exchanged chips 9.

[0064] In addition, in the above example, without specifying individual players 6, the win-loss history for each playing position 7 and the amount of chips obtained (winning amount) may be monitored. In this case, when each player 6 leaves the table, that player 6 cannot be tracked. However, it is possible to detect abnormal situations such as a state where the amount of bet chips is small when losing and large when winning at a specific playing position 7 on one gaming table 4 continuing for several games. When such a playing position 7 is detected, there is a suspicion of fraud or error at that playing position 7. By verifying the video taken of that playing position 7, fraud or error can be discovered.

[0065] Specifically, the camera 2 is installed to photograph at least the chips 9 placed in the betting area 8 of the gaming table 4. The image analysis device 12 analyzes the image taken by the camera 2 to detect for each player position 7 in which position among the player, banker, and tie positions in the betting area 8 the chips are placed and the amount of the chips placed. Also, 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 acquisition amount) for each playing position 7 based on the position (player, banker, or tie) within the betting area 8 where the chips 9 are placed and the win-loss result of the game. Note that only one of the win-loss history and the chip acquisition amount may be recorded. The control device 14 identifies this player position 7 as a playing position suspected of fraud when the history of this win-loss history and / or chip acquisition amount is an abnormal situation (set by the casino) compared to the statistical data of a large number (big data) of past games.

[0066] When an irregularity is suspected for a certain player position 7, the fraud detection system may generate an alarm (light, sound, vibration) so that at least the dealer can perceive it at that time. As a result, it is possible to prevent the continuation of the irregularity by interrupting the subsequent game at least on the spot. Further, information indicating that an irregularity is suspected may be added to the video captured and recorded by the camera 2. Thus, by checking the video, the cause of the suspicion of the irregularity can be investigated.

[0067] The fraud detection system in the casino having the gaming table in the present embodiment further has a function of inspecting the exchange of bills and chips, which is often performed on the gaming table 4. In a casino such as a casino, before the game, the player 6 exchanges bills (such as cash) for gaming chips at a predetermined chip exchange. However, when the player 6 runs out of chips, without leaving the gaming table 4, the player can exchange cash (bills) for chips 9 on the gaming table (such as a baccarat table) and continue the game. However, this creates an opportunity for fraud between the dealer 5 and the player. The exchange of cash (bills) for chips 9 on the gaming table (such as a baccarat table) needs to be done when the game is not in progress. The card distribution device 3 can detect the start of card dealing and the end of dealing (the time of determining the win or loss) in order to determine the outcome of the game. For this reason, in the card distribution device 3, a situation other than card distribution (dealing) is detected, and the control device 14 detects that the exchange of bills and chips 9 is being performed on the gaming table 4 in a situation other than during card dealing (shown in FIG. 6). Whether during card dealing (or other situations) can be detected based on information obtained from the operation of the card distribution device 3 or the dealer 5.

[0068] The control device 14 can perform image analysis on the surface of the bill K to recognize the number and amount of the bills. Further, on the gaming table 4, whether the bill K for exchange with the chip 9 is genuine is determined by detecting the genuine mark G of the bill by irradiating it with a black light. As shown in FIG. 6, the control device 14 also performs image analysis and verification on this genuine mark G, recognizes the total amount of genuine bills, and can recognize the total amount of chips even when a plurality of chips placed on the gaming table as exchange targets are hidden due to the blind spot of the camera 2. It has an artificial intelligence utilization type or deep learning structure that can compare the total amount of the bills K issued by the player on the gaming table 4 with the total amount of the chips 9 issued by the dealer 5 and determine whether the amounts of both match.

[0069] The control device 14 has an artificial intelligence utilization type or deep learning structure that can perform comparative calculations to determine whether the total amount of the chips 9 in the chip tray 17 of the dealer 5 on the gaming table 4 has increased or decreased according to the payment amount of the chips corresponding to the exchanged bills after the exchange of bills and chips has been carried out and settled. It is conceivable that the total amount of the chips 9 in the chip tray 17 of the dealer 5 is always grasped in advance by means of RFID or the like of the chips 9. Also, by photographing the chip tray 17 containing the chips 9 with the camera 2 and analyzing the image with the image analysis device 12, the total amount of the chips 9 contained in the chip tray 17 can be detected.

[0070] Also, the control device 14 verifies whether the increase or decrease in the amount of the chips 9 in the chip tray 17 before and after the exchange of bills and chips matches the chip exchange amount in the image analysis result on the gaming table 4. The amount of the paid bill may be input to the control device 14 by the dealer 5 through key input or the like, or it may be specified by photographing the gaming table 4 where the bill is paid with the camera 2 and analyzing the image with the image analysis device 12.

[0071] As described above, the control device 14 determines whether the amount of chips 9 reduced from the chip tray 17 due to the exchange of bills and chips matches the amount of the bills paid from the player 6 to the dealer 5. Further, after the exchange of bills and chips is made and settled, the control device 14 is an intelligent control device capable of comparing and calculating whether the amount of bills deposited by the dealer 5 (usually by key input or the like) matches the calculated amount of the bills in the image analysis result by the image analysis device 12. Furthermore, it may have an artificial intelligence utilization type or a deep learning structure.

[0072] Furthermore, the control device 14 has an artificial intelligence utilization type or a deep learning structure capable of comparing and calculating whether the total amount of bills deposited by input of the dealer in the game table 4 assigned to the dealer matches the total amount of the bills in the image analysis result by the image analysis device 12.

[0073] The control device 14 compares and determines whether the amount of the chips 9 grasped in the chip tray 17 of the dealer 5 on the game table 4 has increased or decreased according to the payment amount of the chips 9 corresponding to the exchanged bills or the payment amount of the bills corresponding to the exchanged chips 9 after the exchange of the bills and the chips 9 is made.

[0074] (Second Embodiment) Among many table games played in a casino or the like, there are baccarat and blackjack. These games use a standard deck of 52 playing cards and are equipped with a plurality of decks (6 to 9 or 10 decks) that have been shuffled in advance. The playing cards are distributed onto the game table from a card distribution device, and the outcome is determined based on the number (rank) of the distributed cards and the game rules.

[0075] The distribution of cards from the card distribution device and the settlement of bets to the customers (game participants) are performed by the dealer or the like in charge of the game table. In a casino or the like, attempts are being made to prevent mistakes and fraudulent acts in the settlement of bets to the customers (game participants).

[0076] In the card game monitoring system described in International Publication WO2015 / 107902, a surveillance camera is used to read the movement of chips and check whether winnings are paid to the winner.

[0077] Regarding the bets placed by customers and the settlement of bets from the dealer to the customers (game participants) in baccarat and blackjack, there is a problem that it is impossible to detect the timing at which these are carried out, who placed or took the chips, and thus it is impossible to determine whether these are correct.

[0078] To solve the above various problems, the fraud detection system according to the second embodiment is a fraud detection system in a casino having a gaming table, a game monitoring device that monitors the progress of the game being played on the gaming table using a camera, an image analysis device that analyzes the video obtained from the camera, a card distribution device that determines and displays the winning and losing results of each game on the gaming table, a control device that, in each game, uses the analysis result of the image analysis device to identify the position of the chips placed by the game participants on the gaming table, and further uses the winning and losing results to determine the winners and losers among the participants in each game, and is provided with, the control device further 1) In each game, whether there is any movement of the chips after the card draw is started or between the dealer's game start operation and before the winning and losing result of the game is displayed by the card distribution device, 2) After the end of each game, whether there is any movement of the chips by a person other than the dealer while the dealer is collecting the chips wagered by the losing game participants, 3) After the end of each game, whether any chips are added while the dealer is collecting the chips wagered by the losing game participants, 4) After the end of each game, whether payment has been made to the position of the chips wagered by the winning game participants. 5) After each game, determine whether the winner among the game participants has taken the wagered chips and the paid chips. It is provided with at least one function of:

[0079] Furthermore, the control device may be configured to determine at least one of the above (1) to (5) by detecting the movement of the hands of the dealer and the game participants, the movement of the chips, or the movement of the hands and the chips using the analysis result of the image analysis device.

[0080] Furthermore, the control device may be configured to determine whether the amount of chips paid by the dealer to the winner is correct based on the amount wagered by the winner among the game participants.

[0081] Furthermore, the game fraud detection system may further include a monitor or a lamp that gives a warning or display in response to the determination result.

[0082] According to the fraud detection system of the present embodiment, regarding the bets by customers and the settlement of bets by the dealer to customers (game participants) in baccarat and blackjack, it is possible to detect the timing when these are carried out, who placed or took the chips, detect these mistakes and fraudulent acts, give a warning or display, and lead to prevention of recurrence.

[0083] Before entering the detailed description of the present embodiment, the flow of a baccarat game conducted in a casino or the like will be described. In the second embodiment, the same components as those in the first embodiment will be described with the same numbers.

[0084] As shown in FIG. 7, in the gaming table 4, a customer (game participant / player) 6 sits on a play position (chair) 7 facing the dealer 5. Then, as the winning or losing result of the baccarat game, the customer (game participant) 6 bets on whether the player or the banker wins, or a tie occurs, by placing chips 9 in the bet area 8 in front of him / her (hereinafter, this is referred to as "bet"). Then, the dealer 5 measures the timing to end the bet by the customer (game participant) 6 and calls "No More Bet (end of bet acceptance)", and moves his / her hand horizontally, etc. (the state shown in FIG. 7). In the baccarat game, after "No More Bet (end of bet acceptance)" is called and the card drawing is started or after the dealer 5 performs an operation to start the game, until the winning or losing result of the game is displayed by the card distribution device 3, the customer (game participant) 6 cannot move the chips, place additional chips as bets, or take back the chips that have been bet once.

[0085] After that, the playing cards 1 are pulled out one by one from the card distributor 3 onto the gaming table 4 with the back side facing up. First, four cards are pulled out. As shown in the circles 1 to 4 in FIG. 8, the first card goes to the player, the second card goes to the banker, the third card goes to the player, and the fourth card goes to the banker, and they are distributed and placed in the front area 10 (player area 10P and banker area 10B) as seen from the dealer 5 on the gaming table 4. Then, based on the rank (number) of the first to fourth cards 1 and the conditions in the detailed rules of the baccarat game, the dealer 5 pulls out the fifth card 1 and further the sixth card 1, and these become the hands of the player or the banker. Then, based on the rank (number) of the first to fourth (and in some cases, the fifth and sixth combined) cards 1 and the detailed rules of the baccarat game, the outcome of the game is determined. Here, the rules of the game are programmed in advance in the card distributor 3, and it has a structure that can read the information (rank (number) and suit) of the distributed cards 1 and determine the outcome of the game. Whether the win / loss determination result (win / loss result) determined by the card distributor 3 matches the win / loss result determined by the dealer or the like as described above is determined.

[0086] The overall outline of the fraud detection system in the game at the casino according to the embodiment of the present invention will be described below. FIG. 7 is a diagram showing the overall outline of the system. The fraud detection system in the game at the casino includes a game recording device 11 that records the progress state of the game being played on the gaming table 4 as a video via a camera 2, including the customers (game participants) 6 and the dealer 5, and an image analysis device 12 that analyzes the recorded video of the game progress state. Further, it is provided with a card distribution device 3 having a function of determining and displaying the winning or losing result of each game on the gaming table 4. The card distribution device 3 is a so-called electronic shoe that is already used by those skilled in the art, and the rules of the game are programmed in advance. It can detect the timing when the card 1 is distributed by the dealer 5 at the start of each game, read the information (rank (number) and suit) of each distributed card 1, and determine the winning or losing of the game. For example, in the baccarat game, the win of the banker, the win of the player, and the tie (draw) are basically determined by the ranks of 2 - 3 cards respectively, and the determination result (winning or losing result) is displayed on the display lamp 13.

[0087] The control device 14 of this fraud detection system has a chip detection function that uses the analysis result of the image analysis device 12 in each game to identify whether the customer 6 (game participant) bets the chip 9 on the player side or the banker side betting area 8 on the gaming table 4. It is assumed that the position and total amount of the chip 9 (which betting area 8 on the player side or the banker side the chip 9 is bet on) cannot usually be read, such as when the chips 9 are displaced and overlap, or when it becomes a blind spot from the position of the camera 2. The control device 14 is configured to be able to accurately grasp the position, number, etc. by using an existing artificial intelligence - utilized computer or control system, self - learning function, etc. based on deep learning (structure) technology to recognize the hiding due to the blind spot of the chip 9 (when a part of a single chip is hidden or the entire chip is hidden). Further, the structure for detecting the position and type of the chip 9 in the betting area 8 is not limited to this. For example, it may be configured to detect by reading the ID embedded in the chip.

[0088] As described above, the control device 14 can grasp the position (position where bets were made on player, banker, or pair) and type (different values ​​are assigned to each color of chips 9) of chips bet by each player 6 through the camera 2 and the image analysis device 12, and can detect which customer 6 bet on the player (if there are multiple customers 6 who bet on the player, which customer 6 bet the most) and which customer 6 bet on the banker (if there are multiple customers 6 who bet on the banker, which customer 6 bet the most). The image analysis device 12 and the control device 14 in this fraud detection system are structured as a composite of a computer, program, and memory, which may be one or more components.

[0089] The control device 14 is structured to be able to compare the rank and suit information obtained by the image analysis device 12 from the image (using the camera 2) of each card 1 dealt at the gaming table 4 with the rank and suit information read by the card distribution device 3 to determine whether they match. According to the outcome of each game determined by the card distribution device 3, the control device 14 determines whether the collection of losing chips 9 bet by customers (game participants) 6 and the payment of winning chips to winning customers (game participants) 6 were properly carried out according to the outcome of the game by analyzing the image of the game progress via the image analysis device 12.

[0090] The control device 14 has the following functions 1) to 5) as characteristic functions of the present invention, and judges whether or not any cheating that violates the rules is taking place according to the rules of the baccarat game. That is, 1) In each game, from the signal from the card dealing device 3 to start drawing out cards, or from the game start operation by the dealer 5 pressing the start button 4s, until the result of the game is displayed by the card dealing device 3, the image analysis device 12 uses the camera 2 to monitor for any movement of the chips 9 (as shown in Figure 8). 2) After each game, while the dealer 5 is collecting the chips 9 wagered by the losers among the game participants 6 (as shown in FIG. 9), the image analysis device 12 monitors whether the loser 6 has taken the chips 9 illegally, based on the information obtained using the camera 2. 3) After each game, while the dealer 5 is collecting the chips 9 wagered by the losers among the game participants, the image analysis device 12 monitors whether anyone other than the dealer 5 (the winner or the loser) has added winning chips 9W or repositioned new chips 9 on the winning side that were not wagered, based on the information obtained using the camera 2. 4) After each game, the image analysis device 12 monitors whether the correct payout chips 9W have been placed at the position of the chips 9 wagered by the winners among the game participants 6 (as shown in FIG. 10), based on the information obtained using the camera 2. 5) After each game (when the dealer 5 operates the card distribution device 3 to display the win / loss result on the display lamp 13), the image analysis device 12 monitors whether the winner 6W among the game participants 6 has taken the wagered chips 9 and the paid-out chips 9W (as shown in FIG. 11), based on the information obtained using the camera 2.

[0091] The control device 14 analyzes the information obtained by the image analysis device 12 using the camera 2 as follows. That is, using the analysis result of the image analysis device 12, it monitors the movements of the hands of the dealer 5 and the game participants 6, the movements of the chips, or the movements of the hands and the chips to perform the monitoring in 1) to 5) above. In the basic analysis, it is at least necessary to know who has taken the chips 9. The method of this analysis will be described below with reference to FIGS. 12 to 14.

[0092] Analysis of the dealer 5 taking the chips 9 wagered by the game participant 6L (FIG. 12). The dealer 5 collects the chips 9 wagered by the losing game participant 6L in the game. The image analysis device 12 uses the camera 2 to analyze and monitor the information obtained to determine whether the chips are surely collected. First, the change from the state where the wagered chips 9 exist (Figure 12A) to the state where they do not exist (Figure 12C) is detected by image analysis. Then, the image (Figure 12B) between the state where the chips 9 exist and the state where they do not exist is analyzed. In the image (Figure 12B) between the state where the chips 9 exist and the state where they do not exist, it is analyzed from which direction the hand 5h extends (from above in Figure 12 or otherwise). If it extends from above (or a hand appears from above and then moves upward), the hand 5h is determined to be that of the dealer 5, and fraud is detected based on the rule that if the hand extends from any other direction, it is determined to be illegal.

[0093] While the dealer 5 is collecting the chips 9 wagered by the losing game participant 6L in the game, it is monitored whether other persons fraudulently take the losing chips 9 (Figures 12 and 11). In the image between the state where the chips 9 exist and the state where they do not exist, as shown in Figure 13, the analysis of whether the loser 6L or the like among the game participants 6 took the chips is to detect by image analysis that the hand 6h extends (or moves) from below in Figure 13 (originally from above), and it is determined that this means that a hand 6h or the like other than the dealer 5 takes the chips 9, and it is determined that there is fraud.

[0094] Analysis of whether the dealer 5 correctly pays (places) the winning chips 9W to the winning chips 9 and the winner 6W among the game participants 6 takes them. First, for the winning chips shown in Figure 14A, the chips 9W are repaid according to the game rules as shown in Figure 14B. The change from the state shown in Figure 14A to the state shown in Figure 14B is detected, and at the same time, it is detected by image analysis whether the hand is that of the dealer 5's hand 5h. After that, as shown in Figure 14C, now the hand 6h of the winner 6W among the game participants 6 extends (moves) into the same wagering area, and then the control device 14 checks from the image analysis result whether all the chips 9 disappear (the state in Figure 14D) and determines whether there is no fraud according to the game rules.

[0095] Furthermore, the control device 14 is configured to determine whether the amount of chips paid to the winner by the dealer 5 is correct based on the amount wagered by the winner 6W among the game participants 6. A specific example is shown below. The position of the chips 9 and the total amount (whether the chips 9 are wagered in the player-side or banker-side betting area 8) are normally assumed to be unreadable, such as when the chips 9 are displaced and overlapping, or when there are blind spots from the position of the camera 2. The control device 14 uses an existing computer or control system utilizing artificial intelligence, deep learning (structure) technology, self-learning functions, etc., to recognize the hiding due to blind spots of the chips 9 (when a part of a single chip is hidden or when the entire chip is hidden), and is configured to accurately grasp the position, number, etc. Furthermore, the structure for detecting the position 8 and type in the betting area 8 of the chips 9 is not limited to this, and for example, it may be configured to detect by reading the ID embedded in the chips.

[0096] As described above, the control device 14 can grasp the position 8 (the position wagered on the player, banker, or pair), type (the chips 9 are assigned different face values for each color), and number of the chips 9 wagered by each player 6 via the camera 2 and the image analysis device 12, and can detect which customer 6 wagered on the player (if there are multiple customers 6 who wagered on the player, which customer 6 wagered the highest amount), and which customer 6 wagered on the banker (if there are multiple customers 6 who wagered on the banker, which customer 6 wagered the highest amount).

[0097] Furthermore, the control device 14 of the cheating detection system of this game analyzes and monitors the information obtained by the image analysis device 12 using the camera 2 in the above-described manner in accordance with the rules of the baccarat game. The monitoring shown in the aforementioned 1) to 5) is performed to determine whether any cheating contrary to the rules is being committed. When cheating is detected, the card distribution detection device 14C lights the abnormal display lamps 16 provided respectively on both the card distribution device 3 and the gaming table 4, and outputs the detection of cheating wirelessly or by wire to the casino management department or the like at 15. A monitor or a lamp that gives a warning or display in response to the determination result may be provided at another location.

[0098] As described above, cheating acts are detected by the control device 14, and at the time of detection or at an appropriate timing, a display signal is sent to the display lamp 13 and the abnormal display lamp 16 of the card distribution device 3. In addition to giving a warning, a function of preventing the distribution of the cards possessed by the card distribution device 3 after the time when cheating or an error is detected may be activated to prevent the distribution of the card 1.

[0099] Next, an embodiment of the card distribution device 3 used in the table game system of the present invention will be described with reference to FIGS. 15 to 19. The card distribution device 3 includes a card storage unit 102 that stores a plurality of shuffled playing cards 1s, and when the dealer 5 or the like manually pulls out the shuffled playing cards 1 one by one from the card storage unit 102 toward the game table 4, a card guide unit 105 that guides the shuffled playing cards 1, an opening 106 for taking out the card 1 guided by the card guide unit 105, a card detection unit (card detection sensors 22 and 23) that detects when the shuffled playing card 1 is pulled out, a card reading unit 108 that reads information representing at least the number (rank) of the shuffled playing cards 1, a control unit 109 that determines the outcome of the card game based on the number (rank) of the shuffled playing cards 1 sequentially read by the card reading unit 108, a result display lamp 13 that displays the outcome result determined by the control unit 109, a distribution restriction device 30 provided at the opening 106 that restricts the entry and exit of the card 1 from the card storage unit 102, and a management control unit 114 having the same function as the control device 14. These are integrated, and when the control device 14 detects a dealer's mistake or illegal act in the game, it has a function to prevent further cards from being pulled out from the card distribution device 3 after the detection time or at a predetermined timing.

[0100] Next, the distribution restriction device 30 that restricts the insertion and removal of the card 1 from the card storage unit 102 will be described with reference to FIGS. 17 and 18. The distribution restriction device 30 is provided on the card guide 107 of the card guide unit 105 that guides the cards 1 taken out one by one from the front opening 106 of the card storage unit 102 onto the gaming table 4. The distribution restriction device 30 has a structure in which when the card 1 passes through the slot 33 between the card guide unit 105 and the guide cover of the card guide 107, the lock member 34 presses the card 1 to prevent the card 1 from entering and exiting the slot 33. The lock member 34 can take two states: a position (restricted position) where it presses the card 1 and a passable position where the card 1 can pass through, and it moves as shown by the arrow m so as to be able to take these two states. The drive unit 35 is controlled by a control unit 109 that is directly or indirectly connected to the control device 14 by wire or wirelessly, and moves the lock member 34 between two states: a position where it presses the card 1 and a passable position where the card 1 can pass through. The rules of the baccarat game are pre-programmed and stored in the control unit 109.

[0101] Next, a modified example of the distribution restriction device 30 will be described with reference to FIG. 18B. In the modified example, the distribution restriction device 40 has a structure in which when the card 1 passes through the slot 33 between the card guide unit 105 and the card guide 107 (guide cover), the lock member 36 protrudes into the slot 33 to prevent the movement of the card 1. The lock member 36 can take two states: a position (restricted position) where it prevents the movement of the card 1 and a passable position where the card 1 can pass through, and it moves as shown by the arrow m so as to be able to take these two states. The drive unit 37 is controlled by a control unit 109 connected to the control device 14, and moves the lock member 36 between two states: a position where it prevents the movement of the card 1 and a passable position where the card 1 can pass through.

[0102] Next, the details of the code reading unit 108 that reads the code 52 representing the number (count, rank) of the card 1 when the card 1 is manually drawn from the card storage unit 102 will be described. FIG. 17 is a plan view of the main part of the card distribution device 3. In the figure, the code reading unit 108 is provided in the card guide unit 105 that guides the card 1 taken out one by one manually from the opening 106 in front of the card storage unit 102 onto the gaming table 4. The card guide unit 105 is an inclined surface, and card guides 107 that also serve as sensor covers are attached to the edge portions on both sides. Each of the two card guides 107 can be detachably attached with screws or the like (not shown). When the card guide 107 is removed, the sensor group 115 of the code reading unit 108 is exposed. The sensor group 115 is composed of four sensors, namely, two ultraviolet reaction sensors (UV sensors) 20, 21 and object detection sensors 22, 23.

[0103] The object detection sensors 22, 23 are fiber optic sensors that detect the presence or absence of the card 1 and can detect the movement of the card 1. The object detection sensor 22 is located on the upstream side along the flow direction of the card 1 in the card guide unit 105, and the other object detection sensor 23 is located on the downstream side. As shown in the figure, both object detection sensors 22, 23 are provided on the upstream side and the downstream side with the UV sensors 20, 21 interposed therebetween. The UV sensors 20, 21 are equipped with LEDs (ultraviolet LEDs) that emit ultraviolet rays and detectors. On the card 1, the mark M of the code 52 is printed with ultraviolet light emitting ink that emits color when irradiated with ultraviolet rays. When the card 1 is irradiated with ultraviolet rays (black light), the reflected light of the mark M of the code 52 on the card 1 is detected by the detector. The UV sensors 20, 21 are connected to the code reading unit 108 and the control unit 109 via cables. In the code reading unit 108, from the output signals of the detectors of the UV sensors 20, 21, the combination of the marks M is determined and the number (rank) corresponding to each code 52 is determined.

[0104] Based on the detection signals of the object detection sensors 22 and 23, the start and end of reading by the UV sensors 20 and 21 are controlled by the control unit 109. Also, the control unit 109 determines whether the card 1 has passed through the card guide unit 105 normally, based on the detection signals of the object detection sensors 22 and 23. As shown in FIG. 19, square marks M representing the rank (number) and suit (such as heart or spade) of the card are arranged in two rows and four columns at the edge of the card 1. When the UV sensors 20 and 21 detect the mark M, they output an on-signal. The code reading unit 108 determines the relative relationship between the two signals input from the two UV sensors 20 and 21. Thereby, the code reading unit 108 identifies the code based on the relative differences between the two marks M detected by the two UV sensors 20 and 21, and identifies the number (rank) and type (suit) of the corresponding card 1.

[0105] The relationship between the code 52 and the output of the on-signals of the two UV sensors 20 and 21 is shown in FIG. 19. Based on the comparison result of the relative changes in the output of the on-signals of the UV sensors 20 and 21, a predetermined combination of the marks M can be identified. As a result, there are 4 types of combinations of the marks M in the upper and lower two rows, and when these are printed in 4 columns, 256 types of codes can be configured. Each of the 52 types of playing cards is assigned to one of the 256 types of codes, and this is stored in memory or a program as a look-up table. The code reading unit 108 is configured to identify the number (rank) and type (suit) of the card 1 from a predetermined look-up table (not shown) by identifying each code 52. Also, since the 256 types of codes can be associated with the 52 types of cards in a free combination and stored in a look-up table, the combination can be made complex, and the combination of the 256 types of codes and the 52 types of cards can be changed according to time and location. The code is printed with a paint that is visualized by receiving ultraviolet light, and it is desirable that it is printed at a position that does not overlap with the card type notation or the index 103.

[0106] In the above-described embodiment, the image analysis device 12 and the control device 14 are devices having an artificial intelligence utilization type or a deep learning structure. Specifically, the image analysis device 12 and the control device 14 may perform image analysis and the various types of control described above using, for example, a Scale-Invariant Feature Transform (SIFT) algorithm, a Convolutional Neutral Network (CNN), deep learning, machine learning, or the like. These technologies are technologies for performing image recognition on a captured image to recognize an object included in the image. In particular, in recent years, high-precision object recognition has been performed using deep learning technology in which neural networks are multi-layered. This deep learning technology generally recognizes an object with high precision by stacking layers in multiple stages in an intermediate layer between the input layer and the output layer of a neural network. In this deep learning technology, in particular, convolutional neural networks have attracted attention for having higher performance than recognizing an object based on conventional image feature amounts.

[0107] In a convolutional neural network, a recognition target image with a label is learned to recognize the main object included in the recognition target image. When there are a plurality of main objects in the learning image, they are specified by a region rectangle, and learning is performed by attaching a label to the image corresponding to the specified region. Furthermore, in a convolutional neural network, it is also possible to determine the main object in the image and the position of the object.

[0108] To further explain the convolutional neural network, in the recognition process of the target, candidate regions are extracted based on local features by performing edge extraction processing or the like on the recognition target image, and after extracting the feature vectors by inputting the candidate regions into the convolutional neural network, classification is performed, and the candidate region with the highest confidence level after classification is obtained as the recognition result. The confidence level is a quantity indicating to what extent the similarity of the main body of the image learned together with a certain image region and the label is relatively higher than the similarity of other classes.

[0109] Note that devices having an artificial intelligence utilization type or a deep learning structure are described in U.S. Patent No. 9,361,577, U.S. Patent Publication No. 2016-171336, U.S. Publication No. 2015-036920, Japanese Patent Publication No. 2016-110232, etc., and these descriptions are incorporated herein by reference.

[0110] As described above, various embodiments of the present invention have been described. However, it goes without saying that the above-described embodiments can be modified by those skilled in the art within the scope of the present invention, and the device of the present embodiment may be appropriately modified according to the requirements in the applied game.

Explanation of Reference Numerals

[0111] 1 Playing Card 1s A plurality of shuffled playing cards 2 Surveillance Camera 3 Card Distribution Device 4 Gaming Table 5 Dealer 6 Customer (Game Participant / Player) 7 Chair 8 Betting Area 9 Chip 10 Area 10P Player Area 10B Banker Area 11 Game Recording Device 12 Image Analysis Device 13 Result Display Lamp 14 Control Device 14C Card Distribution Detection Device 15 Output (Abnormality Judgment Result, etc.) 16 Abnormality Indicator Lamp 30 Distribution Limiting Device 33 Slot 34 Locking Member 35 Driving Part 36 Locking Member 37 Driving Part 40 Distribution Limiting Device 102 Card Storage Section 103 Index 105 Card Guide Section 106 Opening 107 Card Guide 109 Control Section 112 Side Monitor

Claims

1. A chip identification system for identifying a gaming chip when one or more stacks of gaming chips each having an RFID tag with an ID stored therein are placed on a table, the chip identification system comprising: a reading system that reads the RFID tag of the gaming chip placed on the table to obtain IDs of the gaming chips that constitute the one or more stacks; a camera that captures an image of the one or more stacks placed on the table, the camera having an oblique viewing angle to capture top and side images of gaming chips that constitute the stacks placed on the table; an image recognition device that utilizes artificial intelligence or deep learning techniques to analyze the image and recognize the gaming chips placed on the table, thereby recognizing the one or more stacks; A recognition system that recognizes the type and number of the gaming chips constituting the one or more stacks based on the ID read by the reading system, and recognizes the number of the gaming chips constituting the one or more stacks by analyzing the image; A chip determination system comprising:

2. 2. The chip judgment system according to claim 1, wherein, when one stack is placed on the table, the recognition system recognizes IDs of a plurality of gaming chips constituting the one stack.

3. The chip determination system according to claim 1 , wherein the recognition system recognizes a number of the one or more stacks recognized by the image recognition device.

4. The chip determination system according to claim 1 , wherein the recognition system recognizes the types of the gaming chips constituting the one or more stacks by analyzing the image using artificial intelligence or deep learning technology.

5. 2. The chip determination system according to claim 1, wherein the recognition system analyzes the image using artificial intelligence or deep learning technology to recognize, for each of the one or more stacks, the types and numbers of the gaming chips that constitute the stack.

6. a player identification device that identifies a player playing at the table by face recognition or by reading a member card; 2. The chip determination system according to claim 1, further comprising: a control device that identifies the player who placed the gaming chip on the table based on an identification result of the player identification device.

7. 7. The chip judgment system according to claim 6, further comprising: a chip determination unit that determines whether or not a player has placed a gaming chip on the table, and determines whether or not a player has placed a gaming chip on the table.

8. The chip determination system of claim 1, wherein the recognition system further recognizes the position of the one or more stacks based on information read using the reading system, and / or recognizes the position of the one or more stacks by analyzing the image using artificial intelligence or deep learning technology using the image recognition device.

9. 7. The chip determination system according to claim 6, further comprising a determination device that determines stacks to be collected according to a game result and stacks to be paid according to a game result based on the positions of the one or more stacks recognized by the image recognition system.

10. The tip determination system according to claim 9 , wherein the determination device determines whether the stack to be collected has been correctly collected.

11. 10. The tip determination system according to claim 9, wherein the determination device determines whether the payout has been made correctly to the stack that is to receive the payout.

12. The chip determination system according to claim 10, wherein the determination device determines whether a correct amount of gaming chips has been collected.

13. The chip determination system according to claim 11, wherein the determination device determines whether a correct amount of gaming chips has been paid.

14. The chip determination system according to claim 1 , wherein the recognition system recognizes the one or more stacks placed in the same area as separate stacks.

15. 15. The chip determination system of claim 14, wherein the recognition system recognizes the one or more stacks as separate stacks based on a timing at which the one or more stacks were placed in the same area.

16. The tip determination system according to claim 6 , wherein the control device determines, for each stack, who placed the stack.

Images