Archive for the ‘Card Counting’ tag
Who’s Counting?
Movies glorifying card counting may become a thing of the past.
If you’re like me, and you’ve seen the movie 21, you probably think counting cards in Blackjack is the coolest skill you could ever pick up around a casino. However, counting cards may become a near impossibility if University of Dundee graduate Kris Zutis has his way with things. At the age of 22, Zutis has already developed a system which studies visual feeds from cameras to detect card counters for his final-year project in college. Detailed in his research paper ‘Who’s Counting?: Real-Time Blackjack Monitoring for Card Counting Detection,’ Zutis’ program has captured world-wide attention, and Zutis himself has already been invited to computer vision conferences to lecture about his work.
Kris Zutis’ program first uses various visual recognition techniques to collect various bits of information such as contour analysis to detect what cards have been flipped and stereo imaging to measure the height of chip stacks to determine how much has been bet. After the data is collected, the program analyzes a player’s betting patterns and monitors what cards have been seen already. If a player’s actions are suspicious given the known information, the system can alert the casino of its findings.
The system shows considerable promise for commercialisation, and could become an invaluable asset for casinos. Other devices exist to try and combat car counting that use expensive RFID chips. Kris’s method offers significant cost cutting opportunities for casinos while more effectively identifying car counters and detecting dealer errors.
We’ve already seen examples of computer programs which utilize visual data to perform eye-tracking, determine attractiveness, and perform object recognition, and this new breakthrough is just another extension of what can be done with computer vision.
