Abstract: Systems and methods for dynamic collusion score adjustment in gaming environments are disclosed. A processor detects a first anomaly on a first card used by a first player and a second anomaly on a second card used by a second player using shuffler sensors. These anomalies vary from previously taken images. A relationship between these anomalies is detected. Identifiers for the players are determined using machine learning analysis of table image data. An initial collusion-confidence score is calculated based on the anomaly relationship. The system then monitors interactions between the players via ongoing table image analysis. Upon detecting a predefined interaction type, such as physical contact or non-verbal communication, between the players, the processor adjusts the collusion-confidence score associated with the players. This provides a more robust and dynamic assessment of potential collusion by correlating card data with observed player behaviors.

Abstract: Systems and methods are disclosed for tracking the physical condition of individual playing cards in a casino. Sensors within card-handling devices on a casino network collect data on a unique physical playing card across multiple game rounds. This sensor data, reflecting the card's physical state including observable characteristics, is recorded in a map for the card within a data store. This map allows changes in the card's condition, based on its unique physical features and any developing anomalies, to be tracked over time. By analyzing this map, anomalies representing deviations from the card's previously recorded condition are detected. Upon detection, the map is updated with details of the anomaly and its detection context. This enables ongoing monitoring and identification of changes to specific playing cards during their use in a gaming environment.

Abstract: A method and system detect and link anomalous gaming events. A processor, using shuffler sensors, detects a first anomaly on a first card from a first game instance, the anomaly varying from prior card images. In response, a machine learning model analyzes image data from a first gaming table's image sensors to determine unique biometric facial features of a first participant. A first anonymous identifier is generated from these features and stored, linked to first anomaly data. Subsequently, a second anomaly on a second card in a second game instance is detected by shuffler sensors. Image data from a second gaming table is analyzed by the machine learning model to extract unique biometric facial features of a second participant. It is then determined that the second participant's facial features mathematically correspond to the stored first anonymous identifier. A counter associated with the first anonymous identifier is incremented, indicating multiple linked anomaly events.

Abstract: According to one aspect of the present disclosure, a system comprises a processor configured to execute instructions that cause operations to detect, using sensors of one or more card-handling devices (“card-handling device(s)”) in a network, one or more anomalies (“anomaly (ies)”) on one or more cards (“card(s)”) used during play of one or more games (“game(s)”). The game(s) are played at one or more gaming tables (“table(s)”) associated with the card-handling device(s). The anomaly (ies) vary from one or more previously taken images of the card(s). The operations further include, in response to detecting the anomaly (ies), determining, via analysis by a machine learning model of image data captured by one or more image sensors at the table(s), identifiers for participants that played at the table(s) for the game(s) when the anomaly (ies) was/were detected. The operations further include relating, in a memory store associated with one or more collusion-confidence scores, the identifiers.

Abstract: According to one aspect of the present disclosure, a system comprises a processor configured to execute instructions that cause operations to detect, using sensors of one or more card-handling devices (“card-handling device(s)”) in a network, one or more anomalies (“anomaly (ies)”) on one or more cards (“card(s)”) used during play of one or more games (“game(s)”). The game(s) are played at one or more gaming tables (“table(s)”) associated with the card-handling device(s). The anomaly (ies) vary from one or more previously taken images of the card(s). The operations further include, in response to detecting the anomaly (ies), determining, via analysis by a machine learning model of image data captured by one or more image sensors at the table(s), identifiers for participants that played at the table(s) for the game(s) when the anomaly (ies) was/were detected. The operations further include relating, in a memory store associated with one or more collusion-confidence scores, the identifiers.

Abstract: A method or system to, in response to automatic shuffling of a set of cards by a shuffler, detect a first anomaly of a first card of high value that was used during a round of play for a first card game in which a first player participated at a gaming table. The method or system is further to, in response to analysis of shuffler data, detect a relationship between the first anomaly and a second anomaly. The second anomaly is associated with a second card of high value that was used during a round of play for a second card game in which a second player participated. The system or method is further to, in response to detection of the relationship between the first anomaly and the second anomaly, relate via a collusion-confidence score a first identifier for the first player with a second identifier for the second player.

Abstract: According to one aspect of the present disclosure, a system comprises a processor configured to execute instructions that cause operations to, in response to automatic shuffling of a set of cards by a shuffler, detect a first anomaly associated with a first card of high value that was used during a round of play for a first card game in which a first player participated at a gaming table. The processor is further configured to execute instructions that cause operations to, in response to analysis by the processor of shuffler data, detect a relationship between the first anomaly and a second anomaly. The second anomaly is associated with a second card of high value that was used during a round of play for a second card game in which a second player participated.