Blackjack, a popular casino game, is experiencing a growth in the number of casual players attempting to gain an edge over the house by using a technique called card counting. Card counting is a method of tracking the cards dealt to manipulate the player's odds of winning in their favour. We have built a system that detects the card counters by tracking the game as it progresses, monitoring the cards as the player does, and tracking the player's betting patterns. The correlation between the player's betting patterns and the game card count is analysed to determine the likelihood that a player is card counting, and the system alerts the Casino staff upon positive identification of a card counter. The Blackjack tracking system also has the ability to detect dealer errors, by monitoring dealers' actions made during the game and ascertaining whether or not the correct action was taken.

We developed the system through consultations with staff at the Dundee casino, and through user requirements gathering from Blackjack players and dealers. We integrated a large variety of complex algorithms to build the final working system, which shows great promise for commercialisation, and could become an invaluabe asset for casinos.

The system uses a stereo camera (a Point Grey Bumblebee) placed above the Blackjack table to capture a live feed of the game, and software algorithms using methods such as contour analysis,template and feature matching are employed in order to recognise each card as it is dealt. The player's bets are detected using stereo imaging, by measuring the height of the player's chip stack to determine the number of chips that are being bet. Testing was carried out by a range of users, from professional Blackjack dealers to novice players, and concluded that the system is successful at detecting card counters and dealer errors.

This video shows the blackjack system in action. Krists Zutis, the main developer of the system narrates:

This is joint work with Krists Zutis. We are currently working on furthering the blackjack system, with an eye to eventually creating a commercial product.

Paper

More details can be found by reading the following paper, presented at International Conference on Computer Vision Systems (ICVS 2009):

Krists Zutis and Jesse Hoey Who's Counting?: Real-Time Blackjack Monitoring for Card Counting Detection. Proceedings of the International Conference on Vision Systems, Liege, Belgium, 2009 (bibtex)