Bench Press

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.

(Image Credit)

Computers can do some pretty incredible stuff. We’ve seen computers analyze evolutionary trees, master the game of Go, and even take on the challenge of Jeopardy!. However, as amazing as computers are, the one glaring deficit of computers is its inability to extrapolate and make connections, something that comes easy to humans. The culprit is how computers are designed. Computers are built to follow algorithms: a strict set of guidelines which, when executed faithfully, will yield the correct answer. However, ask a computer to build upon these algorithms is a whole different issue. Humans, on the other hand, quickly learn to develop schemas and a general model of understanding. From these basic concepts, we can use deduction to answer a question we’ve never been asked before by combining different skills together to achieve this goal. For example, humans will quickly identify that a certain object on a street is a car, even if we’ve never seen that certain model of car before.

Enter Cognitive-Level Annotation Using Latent Statistical Structure (CLASS), a project that is trying to push computers to recognize specific classes of objects the way humans can. Luc Van Gool of Belgium’s Leuven University (KUL), a member of the CLASS team, sees great promise in CLASS and has already found a marketable use for it in cell phones. Through a mobile service, CLASS will be able to let its users take a picture of an object, say a famous monument, identify what it is, and provide further information to the user via the internet.

“It’s like the object itself becomes the link to further information,” observes Van Gool. He expects the application of this technology to expand rapidly. For instance, cities and museums may offer interactive guided tours or guide books through kooaba.

While CLASS is still a long way off from being complete, it is clearly a giant step towards extending the capabilities of computers and furthering the field of artificial intelligence.