Recognition system

Abstract

This recognition system, which is a system for recognizing chips in a game venue in which a game table is present, is provided with: a game recording device which records, as an image, the state of chips piled on the game table by means of a camera; and a chip determination device which image-analyzes the recorded image of the chip state and determines the number and types of chips bet by a player. The chip determination device is further provided with a function for storing the feature of an image of chips in a prescribed state, and outputting and displaying, as a determined result, the gist of an indistinct determination, when an image obtained from the game recording device is determined as the image in the prescribed state.

Description

Recognition System

[0001] The present invention relates to a recognition system, and in particular to a chip recognition system.

[0002] In games such as baccarat, customers (players) place bets by stacking multiple chips on the table. Therefore, it is necessary to accurately identify the stacked chips. International Publication No. 2008 / 120749 discloses an example of chips used in the game.

[0003] An object of the present invention is to provide a recognition system that can accurately recognize multiple types of objects.

[0004] The chip recognition system according to the first aspect is a chip recognition system for use in an amusement parlor having a gaming table, and comprises: a game recording device that records the state of chips stacked on the gaming table as an image using a camera; and a chip judgment device that performs image analysis of the recorded image of the chip state to determine the number and type of chips bet by a player, wherein the chip judgment device further has a function of storing characteristics of an image of a predetermined state of chips, and when it is determined that the image obtained from the game recording device is an image of the predetermined state at the time of judgment, outputting and displaying a judgment result indicating that the judgment is unclear.

[0005] According to this aspect, the chip determination device stores, for example, an image that reduces the accuracy of chip reading as an image of a predetermined state, and when determining that the image obtained from the game recording device is an image of such a predetermined state at the time of determination, it does not force an answer but outputs and displays an uncertain determination to that effect. This makes it possible to exclude from the determination results of the number and type of chips a determination result that is made by forcing an answer based on an image that reduces the accuracy of chip reading (i.e., a determination result that is likely to be incorrect). In other words, it becomes possible to determine the number and type of chips only from images that can be read accurately, and as a result, it becomes possible to recognize chips with high accuracy.

[0006] The chip recognition system of the second aspect is the chip recognition system of the first aspect, wherein the chip judgment device includes an artificial intelligence device, and the artificial intelligence device learns as training data a plurality of images used in past judgments when the chip judgment device made an error in judgment, and the chip judgment device further has a function of self-judging the accuracy of the judgment based on images in which the judgment result was erroneous as a result of the learning, and outputting and displaying as an judgment result an uncertain judgment for judgments in which there is doubt.

[0007] According to this aspect, the artificial intelligence device of the chip judgment device can improve the accuracy of self-judgment by learning from multiple images used in past (incorrect) judgments when there was an error in the judgment as training data, thereby reducing the number of cases where an image that can be read correctly is erroneously output and displayed as unclear.

[0008] The chip recognition system of the third aspect is the chip recognition system of the second aspect, and when the chip determination device itself determines that the determination is unclear, it further has a function of analyzing the image of the game recording device and determining and storing whether the cause of the determination that the determination is unclear is that the chips are stacked on the gaming table overlap, or that part of or the entire chip is hidden by another chip.

[0009] According to this embodiment, the dealer can easily check the cause of the unclear judgment from the judgment result stored in the chip judgment device. As a result, the dealer can quickly resolve the cause of the unclear judgment by re-placing the chip in a position where it is not shaded by other chips or by neatly stacking chips that are jagged (if the player does not like the dealer touching the chips, the dealer can warn the player).

[0010] The chip recognition system of the fourth aspect is a chip recognition system of any one of the first to third aspects, wherein the game recording device records the images acquired from the camera by assigning an index or time stamp, or by assigning a tag that identifies the stacking state of the chips, so that the record of the game can be later analyzed by the chip judgment device.

[0011] According to this aspect, the chip determination device can easily identify an image of the chip state to be analyzed from the recorded contents of the game recording device by using the index, time, and tag assigned to the image, thereby reducing the time required for identification.

[0012] The chip recognition system of the fifth aspect is a chip recognition system of any one of the first to fourth aspects, wherein the chip judgment device includes a second artificial intelligence device, and the second artificial intelligence device learns, as training data, information on multiple images and chips used in past judgments when the judgment made by the chip judgment device was correct.

[0013] According to this aspect, the second artificial intelligence device of the chip judgment device learns from multiple images and chip information used in past (correct) judgments made by the chip judgment device when the judgment was correct, as training data, thereby improving the accuracy of judgment when determining the number and type of chips.

[0014] The chip recognition system of the sixth aspect is a chip recognition system of any one of the first to fifth aspects, wherein when the chip determination device itself determines that the chip is unclear, it performs image analysis of an image recorded by a camera other than the camera to determine the number and type of chips bet by the player.

[0015] The chip recognition system of the seventh aspect is a chip recognition system of any one of the first to sixth aspects, wherein when the chip determination device recognizes the next chip without recognizing a chip at a certain interval or more in the vertical direction, it determines that the image is in the specified state and outputs and displays a determination result indicating that the determination is unclear.

[0016] The chip recognition system of the eighth aspect is a chip recognition system of any one of the first to seventh aspects, wherein the chip determination device compares the number of chips determined from the height of the chips with the number determined by image analysis of an image of the chip state, and if they differ, determines that the image is in the specified state, and outputs and displays an unclear determination as the determination result.

[0017] A recognition system according to a ninth aspect is a recognition system in which objects to be judged are of multiple types, and the system distinguishes the objects by type and determines the number of each type, and comprises: a recording device that records the state of the objects as an image using a camera; and a judgment device including an artificial intelligence device that analyzes the recorded images of the objects and determines the number of each type of object, wherein the judgment device learns past judgment results as training data and has a function of self-judging the accuracy of the judgment, and further has a function of self-judging that the judgment result is doubtful if the level of accuracy is below a certain level, and outputting and displaying that as the judgment result that the judgment is uncertain.

[0018] According to this aspect, the determination device learns from past determination results as training data, and for a new image, it first self-determines the accuracy of the determination, and if the level of accuracy is below a certain level, it outputs and displays an uncertain determination rather than forcing an answer. This makes it possible to exclude from the determination results of the number of each type of object a determination result that is made for an image with low accuracy in the determination (i.e., a determination result that is likely to be incorrect). In other words, it becomes possible to determine the number of each type of object only from images that can be accurately read, and as a result, it becomes possible to accurately recognize objects.

[0019] FIG. 1 is a diagram schematically showing an amusement center equipped with a chip recognition system according to one embodiment. FIG. 2 is a diagram for explaining the progress of a baccarat game. FIG. 3 is a block diagram showing a schematic configuration of a chip recognition system according to one embodiment. FIG. 4 is a flowchart for explaining a chip recognition method according to one embodiment. FIG. 5 is a diagram for explaining a case where one chip is hidden behind another chip. FIG. 6 is a diagram for explaining a case where chips are stacked in a jagged pattern.

[0020] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In each drawing, components having equivalent functions are designated by the same reference numerals, and detailed description of the components having the same reference numerals will not be repeated.

[0021] In the embodiment described below, a recognition system for chips in an amusement arcade with gaming tables will be described as an example of a recognition system that distinguishes objects by type and determines the number of each type, but it goes without saying that the object to be determined is not limited to chips as long as it has multiple types.

[0022] 1 and 2, a game played in a gaming parlor having a gaming table 4 will be described. In this embodiment, an example will be described in which the gaming table 4 is a baccarat table and a baccarat game is played, but the present invention can also be applied to other gaming parlors or other games.

[0023] Fig. 1 is a diagram schematically illustrating an amusement facility equipped with a chip recognition system 10 according to one embodiment. As shown in Fig. 1, the amusement facility is provided with a substantially semicircular gaming table 4 and a plurality of chairs 201 arranged along the arc side of the gaming table 4 so as to face the dealer D. The number of chairs 201 is arbitrary, and in the example shown in Fig. 1, six chairs 201 are arranged. In addition, a betting area BA is provided on the gaming table 4 corresponding to each chair 201. That is, in the example shown, six betting areas BA are arranged in an arc shape.

[0024] As shown in Fig. 1, customers (players) C are seated at each of the chairs 201. Customers (players) C bet on the outcome of the baccarat game, whether the player or the banker will win, or whether the game will end in a draw (tie), by placing chips W in a pile on a betting area BA provided in front of the chairs 201 where they are seated (hereinafter, this will be referred to as a "bet").

[0025] The chips W to be bet may be of one type only, or may be of multiple types. The number of chips W to be bet may be determined arbitrarily by the customer (player) C. The chip recognition system 10 according to this embodiment recognizes the number and types of the chips W arranged in a stack.

[0026] To end the betting by customer (player) C, dealer D waits for the right timing to call "No More Bet" and moves his hand sideways. Next, dealer D draws cards one by one from card shooter device S onto gaming table 4. As shown in FIG. 2, the first card becomes the player's hand, the second card becomes the banker's hand, the third card becomes the player's hand, and the fourth card becomes the banker's hand (hereinafter, the drawing of the first to fourth cards will be referred to as "dealing").

[0027] All cards are drawn face down from the card shooter S. Therefore, neither the dealer D nor the customer (player) C can know the rank (number) or suit (heart, diamond, spade, club) of the drawn card.

[0028] After the fourth card is drawn, the customer (Player) C who bet on Player (if multiple customers bet on Player, the customer C who bets the highest amount; if no customers bet on Player, the dealer D) turns over the first and third cards that were face down. Similarly, the customer (Player) C who bet on Banker (if multiple customers bet on Banker, the customer C who bets the highest amount; if no customers bet on Banker, the dealer D) turns over the second and fourth cards (this turning over of face-down cards is generally called a "squeeze").

[0029] Then, based on the ranks (numbers) of the first four cards and the detailed rules of the baccarat game, dealer D draws a fifth card and then a sixth card, which become the hand of the player or banker, respectively. Similarly, customer (player) C, who bet on the player, squeezes the cards that will become the player's hand, and customer (player) who bet on the banker squeezes the cards that will become the banker's hand.

[0030] The time from when the first to fourth cards are drawn until the fifth and sixth cards are squeezed and the outcome of the game is revealed is the most exciting time for customer (player) C.

[0031] Furthermore, depending on the rank (number) of the cards, the outcome may be decided by the first four cards, or it may take five or even six cards to finally decide the winner. Dealer D determines that the winner has been decided and the results of the game based on the rank (number) of the squeezed cards, and presses the win / loss result display button on the card shooter device S to display the results on the monitor to inform the customer (player) C.

[0032] At the same time, the outcome of the game is determined by a win / loss determination unit possessed by the card shooter device S. If the dealer D attempts to draw another card without displaying the outcome of the game even though the outcome has been determined, this is an error. The card shooter device S detects this error and outputs an error signal. Finally, while the outcome of the game is being displayed, the dealer D settles the chips bet by the customer (player) C, paying the winning customer (player) C and collecting the chips bet by the losing customer (player) C. After the settlement is complete, the display of the outcome of the game is terminated and betting for the next game begins.

[0033] The above-described flow of a baccarat game is widely practiced in general casinos, and the card shooter device S is an existing card shooter device that has a structure in which cards are drawn by the dealer D, is configured to read the drawn cards, and further has a result display button and result display unit, and is equipped with the function of determining whether or not a player has won or lost and displaying the results of the win or loss. On a general casino floor, a card shooter device S and a monitor are placed at each of the multiple gaming tables 4 lined up, and the cards to be used are supplied in packages or sets, or even cartons, to each gaming table 4 or the cabinet below it, and are operated.

[0034] The chip recognition system 10 of this embodiment relates to a system for recognizing chips W stacked and placed in the betting area BA by a customer (player) C, and more specifically, to a system for recognizing the number and / or type of chips W.

[0035] 1, in this embodiment, a monitoring camera 212 for capturing images of the chips W stacked in the betting area BA is provided outside the gaming table 4. Each chip W is provided with an RFID, and a chip tray 23 managed by the dealer D is provided with an RFID reader 22 for reading the RFID of the chips W in the chip tray 23.

[0036] The chip recognition system 10 according to this embodiment is communicably connected to a surveillance camera 212 and an RFID reader 22 .

[0037] Fig. 3 is a block diagram showing a schematic configuration of a chip recognition system 10 according to this embodiment. As shown in Fig. 3, the chip recognition system 10 includes a game recording device 11, a chip determination device 12, and a determination correctness determination device 14. At least a part of the chip recognition system 10 is realized by a computer.

[0038] The game recording device 11 includes a fixed data storage such as a hard disk. The game recording device 11 records the state of the chips W stacked on the gaming table 4 as an image captured by the camera 212. The image may be a moving image or a series of still images.

[0039] The game recording device 11 may record images acquired from the camera 212 by adding an index or time stamp, or by adding a tag identifying the scene of collecting or paying the chip W, so that the game record can be later analyzed by the chip determination device 12 described below.

[0040] The chip determination device 12 analyzes the image of the state of the chips W recorded in the game recording device 11 to determine the number and type of chips W bet by the customer (player) C. The chip determination device 12 may include an artificial intelligence device that performs image recognition using, for example, deep learning technology.

[0041] However, if the chips W1 to W6 bet by customer (player) C are stacked in multiple piles (see Figure 5) or if the chips W1 to W6 are stacked in a disorderly and jagged manner (see Figure 6), the camera 212 cannot see the entire chips W1 to W6, which may result in a lower accuracy in reading the chips W1 to W6.

[0042] More specifically, if the height of camera 212 is raised, as in camera 212 indicated by the symbol (A) in Figure 5, even if chips W1 to W6 are stacked separately in a front pile and a back pile, chips W1 to W4 in the back pile are less likely to be hidden in the shadow of chips W5 and W6 in the front pile. However, if chips W1 to W6 are stacked in a messy, jagged manner, as in camera 212 indicated by the symbol (A) in Figure 6, a certain chip W1 may be hidden in the shadow of another chip W2 above it, or a certain chip W3 may be hidden in the shadow of other chips W4 and W5 above it, making it difficult to read all of chips W1 to W6.

[0043] Conversely, if the height of camera 212 is lowered, as in camera 212 indicated by the symbol (B) in Figure 6, it is easy to read all of chips W1 to W6 even if the stacking arrangement of chips W1 to W6 is messy and jagged. However, if chips W1 to W6 are stacked in separate piles in the front and back, as in camera 212 indicated by the symbol (B) in Figure 5, chips W1 and W2 in the back pile are likely to be hidden in the shadow of chips W5 and W6 in the front pile, making it difficult to read all of chips W1 to W6.

[0044] Furthermore, even if there is no problem with the way chips W1 to W6 are stacked, if halation (a phenomenon in which external light enters and the image appears white) occurs in camera 212, the contrast of the image will decrease, and the accuracy rate of reading chips W1 to W6 will decrease.

[0045] Conventional AI devices will force an answer (with a high probability of being wrong) even for images with low reading accuracy, and because the answer is wrong, the chips bet by customer (player) C will not match the chips in the chip tray. If the game is stopped every time a match does not occur due to a misreading by the AI ​​device, it will be inefficient.

[0046] Taking these points into consideration, the chip determination device 12 in this embodiment includes, in addition to an artificial intelligence device (artificial intelligence device 12a for chip information determination) that determines the type and number of stacked chips W, an artificial intelligence device (artificial intelligence device 12b for image pattern recognition) that recognizes image patterns with a low accuracy rate (prone to mistakes).

[0047] The artificial intelligence device 12a for determining chip information analyzes the image of the state of the chips W recorded in the game recording device 11 to determine the number and type of chips W bet by the customer (player) C. The artificial intelligence device 12a for determining chip information may further determine the position of the chips W bet by the customer (player) C on the betting area BA.

[0048] The artificial intelligence device 12a for determining chip information may analyze images of the state of the chips W recorded in the game recording device 11 and determine the number and type of chips W in the chip tray 23 before settlement of each game.

[0049] 3, the tip determination device 12 outputs the determination result to the output device 15. The output device 15 may output the determination result of the tip determination device 12 as text information to a monitor on the gaming table 4, or may output it as audio information to a headset of the dealer D, etc.

[0050] Furthermore, the image pattern recognition artificial intelligence device 12b stores the characteristics of images of chips W in a predetermined state and determines whether the image obtained from the game recording device 11 is an image of the predetermined state. Here, an "image of chips W in a predetermined state" is an image in which, when the image is analyzed to determine the number and type of chips, the accuracy of the determination may be below a certain level, i.e., the determination may be questionable. Specifically, for example, an image of chips W1 to W6 stacked in multiple piles taken and stored by a camera 212 positioned low (see the camera 212 indicated by the symbol (B) in FIG. 5), an image of chips W1 to W6 stacked in a messy, jagged manner taken and stored by a camera 212 positioned high (see the camera 212 indicated by the symbol (A) in FIG. 6), an image in which halation occurs, etc.

[0051] When the chip determination device 12 determines that the image obtained from the game recording device 11 is an image of a predetermined state by the artificial intelligence device 12b for image pattern recognition, that is, when the chip determination device 12 determines that the level of accuracy of the determination is below a certain level, the chip determination device 12 outputs a determination result indicating that the determination is unclear to the output device 15.

[0052] In addition, when the chip determination device 12 itself determines that the determination is unclear, it may further have the function of analyzing the image obtained from the game recording device 11 to determine and store whether the cause of the determination that the determination is unclear is (1) whether the chips are stacked on top of each other on the gaming table, or (2) whether part of or the entire chip W is hidden by another chip.

[0053] Referring to Figures 5 and 6, if the chip determination device 12 determines that the image obtained from the camera 212 indicated by the symbol (A) or the camera 212 indicated by the symbol (B) is an image of a predetermined state and is therefore indeterminable, it may read the chip W using an image captured by another camera 212 indicated by the symbol (C). The chip W can be viewed more objectively by viewing from a different angle using a camera oriented or positioned in a different direction. In particular, if the cause of the indeterminable determination is that part or all of the chip W is obscured by another chip, as shown in Figure 5, the opposite camera 212 indicated by the symbol (C) can be used to ensure that the chip is not obscured by the other chip. Furthermore, the chip determination device 12 may output the chip W reading results using the images captured by each camera 212. In this case, the chip determination device 12 may output the accuracy of each reading result together, or the result with the most number of reads may be considered to be the most likely to be correctly recognized.

[0054] When counting chips W, the chip determination device 12 may determine that determination is impossible if it recognizes the next chip W without recognizing any chips at a certain vertical interval or more in a group of chips W. In other words, if it recognizes the next chip W without recognizing any chips at a certain vertical interval or more, there is a high possibility that the chips in between are hidden and not visible.

[0055] The chip determination device 12 may be configured to compare the number of chips W determined from the height of the chips W, etc., with the results of determining the type and number of chips W, and if the number determination results differ, output a determination result that the number cannot be determined. The number may also be determined by determining a specific point (such as the center of the outline of the top chip) from the shape of the chips and using a method such as triangulation.

[0056] The judgment correctness determination device 14 is a device that determines whether the judgment result of the chip determination device 12 is correct or not. When the settlement of the chips bet by the customers (players) C is completed, that is, when all payments to the winning customers (players) C and all collection of the chips W bet by the losing customers (players) C (losing chips) are completed, the judgment correctness determination device 14 grasps the actual total amount V0 of the chips W in the chip tray 23.

[0057] In this embodiment, the judgment correctness determination device 14 acquires RFID information of the chips W in the chip tray 23 from the RFID reading device 22, and based on the acquired RFID information, determines the type and number of chips W in the chip tray 23 after settlement for each game, and grasps the actual total amount V0.

[0058] The judgment correctness determination device 14 also obtains information on the number and type of chips W as the judgment result from the chip determination device 12, and calculates, based on the obtained chip W information, the total amount of chips W (winning chips) bet by the winning customer (player) C (i.e., the reduction amount in the chip tray 23 for that game) V2 and the total amount of chips W bet by the losing customer (player) C (i.e., the increase amount in the chip tray 23 for that game) V3. The judgment correctness determination device 14 then subtracts the reduction amount V2 in the chip tray 23 for that game from the total amount V1 of chips W in the chip tray 23 before settlement for each game, and adds the increase amount V3 in the chip tray 23 for that game to calculate the total amount V4 (=V1-V2+V3) of chips that should be in that chip tray 23.

[0059] The judgment correctness determination device 14 compares the total amount V4 of the chips W in the chip tray 23 with the actual total amount V0 of the chips W in the chip tray 23, and when there is a difference between the total amount V4 and the actual total amount V0 (V4≠V0), it determines that there is an error in the judgment result of the chip judgment device 12. On the other hand, when the total amount V4 of the chips W matches the actual total amount V0 (V4=V0), the judgment correctness determination device 14 determines that the judgment result of the chip judgment device 12 is correct.

[0060] The chip determination device 12 acquires the correctness of the determination result of the chip determination device 12 from the determination correctness determination device 14. If the determination correctness determination device 14 determines that the determination result of the chip determination device 12 is correct, the artificial intelligence device 12a for chip information determination learns, as training data, the image used in the past (correct) determination when the determination was correct and information on the number and type of chips W as the (correct) determination result. By repeating this learning, the artificial intelligence device 12a for chip information determination can improve the accuracy of determining the number and type of chips W.

[0061] On the other hand, if the judgment accuracy determination device 14 determines that the judgment result of the chip judgment device 12 is erroneous, the artificial intelligence device 12b for image pattern recognition learns the image used in the previous (incorrect) judgment when the judgment was erroneous as training data for "images in a predetermined state." Images in a predetermined state (such as an image in which one chip is hidden behind another, an image of chips stacked in a jagged pattern, or an image with halation) may be selected by a person and trained by the artificial intelligence device 12b for image pattern recognition. Images in a predetermined state (such as an image in which one chip is hidden behind another, an image of chips stacked in a jagged pattern, or an image with halation) may be intentionally created by a person or an artificial intelligence and trained by the artificial intelligence device 12b for image pattern recognition. By repeating this type of learning, the artificial intelligence device 12b for image pattern recognition can accurately extract images for which the accuracy of judgment may be below a certain level, i.e., the accuracy of self-judgment can be improved when self-judging the accuracy of judgment.

[0062] Next, an example of the operation of the chip recognition system 10 (chip recognition method) according to this embodiment will be described with reference to FIG.

[0063] As shown in Figure 4, first, when a customer (player) C places chips W in a stack in the betting area BA of the gaming table 4 (the chips W are bet), the game recording device 11 captures and records the state of the stacked chips W as an image using the camera 212 (step S31).

[0064] Next, the tip determination device 12 acquires the image recorded in the game recording device 11. Note that the image acquired by the tip determination device 12 may be selected based on an index, a time, or a tag that identifies a scene of collecting or paying out the tip W, which is assigned to the image by the game recording device 11.

[0065] In the chip determination device 12, the artificial intelligence device 12b for image pattern recognition judges whether or not the image obtained from the game recording device 11 is an image of a predetermined state (step S32). More specifically, as described above, the artificial intelligence device 12b for image pattern recognition learns, as training data, a plurality of images used in past judgments when the chip determination device 12 made an error in judgment, and as a result of this learning, makes a self-judgment on the accuracy of the judgment of the chip W based on the image in which the judgment result was erroneous, and judges whether or not the accuracy of the judgment is below a certain level.

[0066] When the image pattern recognition artificial intelligence device 12b judges that the image obtained from the game recording device 11 is an image of a predetermined state (step S33: YES), the chip determination device 12 outputs a judgment result indicating that the judgment is unclear to the output device 15 (step S40). The judgment result of the chip determination device 12 may be output by the output device 15 as text information to the monitor on the gaming table 4, or may be output as audio information to the headset of the dealer D, etc.

[0067] On the other hand, if the artificial intelligence device 12b for image pattern recognition determines that the image obtained from the game recording device 11 is not an image of a predetermined state (step S33: NO), the artificial intelligence device 12a for chip information determination analyzes the image of the state of the chips W recorded in the game recording device 11 and determines the number and type of chips W bet by the customer (player) C (step S34).

[0068] In step S34, the chip determination device 12 may perform image analysis on the image of the state of the chips W recorded in the game recording device 11 to determine the number and type of chips W bet by the customer (player) C, as well as the position of the chips W bet by the customer (player) C on the bet area BA, or may determine the number and type of chips W in the chip tray 23 before settlement of each game.

[0069] Information on the number and type of chips W determined by the chip determination device 12 is output to the output device 15 (step S35). The determination result of the chip determination device 12 may be output by the output device 15 to a monitor on the gaming table 4 as text information, or may be output as audio information to a headset of the dealer D, etc.

[0070] Information on the number and type of chips W determined by the chip determination device 12 is also input to the determination correctness determination device 14. The determination correctness determination device 14 determines whether the determination result of the chip determination device 12 is correct or not (step S36).

[0071] If the judgment correctness determination device 14 determines that the judgment result of the chip judgment device 12 is correct (step S37: YES), the image used for the (correct) judgment by the chip judgment device 12 and the information on the number and type of chips W as the (correct) judgment result are input as training data into the artificial intelligence device 12a for chip information judgment, and the artificial intelligence device 12a for chip information judgment performs learning (step S38).

[0072] On the other hand, if the judgment correctness determination device 14 determines that the judgment result of the chip judgment device 12 is incorrect (step S37: NO), the image used in the (incorrect) judgment by the chip judgment device 12 is input to the artificial intelligence device 12b for image pattern recognition as training data for the ``image of a specified state,'' and the artificial intelligence device 12b for image pattern recognition performs learning (step S39).

[0073] Artificial intelligence will make big mistakes (confidently give the wrong answer) if there is an error in the judgment result, so by having the artificial intelligence learn image patterns that are likely to be mistaken, it can be made to recognize those image patterns that are likely to be mistaken.

[0074] As described above, according to this embodiment, the chip determination device 12 stores images that reduce the accuracy of chip W reading as images of a predetermined state, and when determining that the image obtained from the game recording device 11 is an image of such a predetermined state at the time of determination, it does not force an answer but outputs and displays an uncertain determination to that effect. This makes it possible to exclude from the determination results of the number and type of chips W determination results that result from a forced answer based on an image that reduces the accuracy of chip W reading (i.e., a determination result that is likely to be incorrect). In other words, it becomes possible to determine the number and type of chips W only from images that can be accurately read, and as a result, it becomes possible to recognize chips W with high accuracy.

[0075] That is, for example, if the accuracy rate is 99.9% when 1,000 images are judged by the chip judgment device 12, and the accuracy rate is low in 9 out of 10 images with 0.1% errors because there are chips in shadow or the chips are stacked in a jagged manner, then the accuracy rate can be raised by another level by excluding such cases from the denominator.

[0076] Furthermore, according to this embodiment, the AI ​​device 12b for image pattern recognition can improve the accuracy of its own judgment by learning from multiple images used in past (incorrect) judgments when there is an error in judgment, thereby reducing the number of cases where an image that can actually be read accurately is erroneously output and displayed as unclear.

[0077] Furthermore, according to this embodiment, when the chip determination device 12 itself determines that the determination is unclear, it determines and stores whether the cause of the determination is (1) whether the chips W stacked on the gaming table 4 are overlapping, or (2) whether part or all of one chip W is hidden by another chip W, so that the dealer D can easily confirm the cause of the determination of unclear. This allows the dealer D to quickly resolve the cause of the unclear determination by repositioning the chip W in a position where it is not hidden by another chip W, or by neatly stacking chips W that are jagged (if the customer (player) C dislikes the dealer D touching the chips W, the dealer D may warn the customer (player) C).

[0078] Furthermore, according to this embodiment, the game recording device 11 records the images acquired from the camera 212 by assigning an index or time, or by assigning a tag that identifies the stacking state of the chips W. Therefore, the chip determination device 12 can use the index, time, or tag assigned to the image to easily identify the image of the state of the chips W to be analyzed from the recorded contents of the game recording device 11, thereby reducing the time required for identification.

[0079] In addition, according to this embodiment, the artificial intelligence device 12a for chip information judgment learns from multiple images used in past (correct) judgments when the judgment in the chip judgment device 12 was correct, and information on the chip W as the (correct) judgment result, as training data, thereby improving the accuracy of judgment when determining the number and type of chips W.

[0080] The above-described embodiments have been described for the purpose of enabling a person having ordinary skill in the art to practice the present invention. Various modifications of the above-described embodiments would naturally be possible for a person skilled in the art, and the technical concept of the present invention may also be applied to other embodiments. Therefore, the present invention is not limited to the described embodiments, but should be accorded the broadest scope in accordance with the technical concept defined by the claims.

Claims

1. A chip recognition system for use in an amusement parlor having a gaming table, comprising: a game recording device that records the state of chips stacked on said gaming table as an image using a camera; and a chip judgment device that analyzes the recorded image of the chip state and determines the number and type of chips bet by a player, wherein said chip judgment device stores the characteristics of an image of a predetermined chip state, and when it determines that the image obtained from said game recording device is an image of said predetermined state at the time of judgment, outputs and displays a judgment result indicating that the judgment is unclear.

2. A chip recognition system as claimed in claim 1, wherein the chip determination device includes an artificial intelligence device, which learns as training data a plurality of images used in past determinations when the chip determination device has made an error in its determination, and the chip determination device further has the function of determining the accuracy of its own determination based on images in which the determination result has been erroneous as a result of said learning, and outputting and displaying as an evaluation result a determination that there is doubt as being uncertain for any determination.

3. A chip recognition system as described in claim 2, further comprising a function for, when the chip determination device itself determines that a chip is unclear, analyzing the images of the game recording device to determine and store whether the cause of the determination that a chip is unclear is that the chips are stacked on top of each other on the gaming table, or that part of or the entire chip is hidden by another chip.

4. A chip recognition system according to any one of claims 1 to 3, wherein the game recording device records the images acquired from the camera by assigning an index or time stamp, or by assigning a tag specifying the stacking state of the chips, so that the record of the game can be later analyzed by the chip judgment device.

5. A chip recognition system according to any one of claims 1 to 4, wherein the chip determination device includes a second artificial intelligence device, and the second artificial intelligence device learns, as training data, information on multiple images and chips used in past determinations when the determination made by the chip determination device was correct.

6. A chip recognition system as claimed in any one of claims 1 to 5, wherein the chip determination device, when it determines that the chip is unclear, performs image analysis of an image recorded by a camera other than the camera to determine the number and type of chips bet by the player.

7. A chip recognition system according to any one of claims 1 to 6, wherein the chip determination device, when recognizing a next chip without recognizing a chip at a fixed interval or more in the vertical direction, determines that the image is in the specified state, and outputs and displays a judgment result indicating that the judgment is uncertain.

8. A chip recognition system according to any one of claims 1 to 7, wherein the chip determination device compares the number of chips determined from the chip height with the number determined by image analysis of the image of the chip state, and if they differ, determines that the image is in the specified state, and outputs and displays a determination result indicating that the determination is unclear.

9. A recognition system in which objects to be judged are of multiple types and the objects are distinguished by type to determine the number of each type, comprising: a recording device that records the state of the objects as images using a camera; and a judgment device including an artificial intelligence device that analyzes the recorded images of the objects and determines the number of objects of each type, wherein the judgment device learns past judgment results as training data and has the function of self-judging the accuracy of the judgment, and further has the function of self-judging that the judgment result is doubtful if the level of accuracy is below a certain level, and outputting and displaying the judgment result as unclear.

Images