This paper describes a computer vision system to detect card counters and dealer errors in a game of Blackjack from an overhead stereo camera. Card counting is becoming increasingly popular among casual Blackjack players, and casinos are eager to nd new systems of deal- ing with the issue. There are several existing systems on the market; however, these solutions tend to be overly expensive, require specialised hardware (e.g. RFID) and are only cost-eective to the largest casinos. With a user-centered design approach, we built a simple and eective system that detects cards and player bets in real time, and calculates the correlation between player bets and the card count to determine if a player is card counting. The system uses a combination of contour anal- ysis, template matching and the SIFT algorithm to detect and recognise cards. Stereo imaging is used to calculate the height of chip stacks on the table, allowing the system to track the size of player bets. Our system achieves card recognition accuracy of over 99%, and eectively detected card counters and dealer errors when tested with a range of dierent users, including professional dealers and novice blackjack players.
All content in this area was uploaded by Jesse Hoey
Content may be subject to copyright.
A preview of the PDF is not available
... Since there is very less published work on table gaming systems which are capable of digitizing the whole game of blackjack, we relied on our industry understanding to evaluate our model. However, we compared our chip and card detection pipeline with the work done by Krists et al. [27] which was evaluated in a constrained setup. ...
... We evaluated the main bet accuracy for the overall bet and also across individual color in the stack as shown in Table I. Krists et al. [27] used a BumbleBee2 stereo camera to calculate the size of the bet. Even though they were able to achieve 99% accuracy on a small dataset, their chip setup was limited to a single color stack whereas our model achieved 95% bet color detection accuracy on a realistic setup (with multiple color stacks in main bet area). ...
... The accuracy numbers for 150 hands are listed in Table III. In a parallel system [27], tested under controlled environment -with only 400 images; essentially testing each card 10 times -the author reported a card face value accuracy of 99.75%. Whereas our proposed system, which was tested in near-real life scenario -with multiple combinations of actual players and dealers achieved a comparable accuracy of card face value of 98% and in few nuances even higher. ...
Annually the gaming industry spends approximately $15 billion in marketing reinvestment. However, this amount is spent without any consideration for the skill and luck of the player. For a casino, an unskilled player could fetch ~4 times more revenue than a skilled player. This paper describes a video recognition system that is based on an extension of the Mask R-CNN model. Our system digitizes the game of blackjack by detecting cards and player bets in real-time and processes decisions they took in order to create accurate player personas. Our proposed supervised learning approach consists of a specialized three-stage pipeline that takes images from two viewpoints of the casino table and does instance segmentation to generate masks on proposed regions of interest. These predicted masks along with derivative features are used to classify image attributes that are passed onto the next stage to assimilate the gameplay understanding. Our end-to-end model yields an accuracy of ~95% for the main bet detection and ~97% for card detection in a controlled environment trained using transfer learning approach with 900 training examples. Our approach is generalizable and scalable and shows promising results in varied gaming scenarios and test data. Such granular level gathered data, helped in understanding player's deviation from optimum strategy and thereby separate the skill of the player from the luck of the game. Our system also assesses the likelihood of card counting by correlating the player's betting pattern to the deck's scaled count. Such a system lets casinos flag fraudulent activity and calculate expected personalized profitability for each player and tailor their marketing reinvestment decisions.
... In [7] describes a computer vision system to detect card counters and dealer errors in a game of Blackjack, the system uses a combination of contour analysis, template matching and the SIFT algorithm to detect and recognize cards. Cooper & Dawson-Howe [8] built a system that recognized cards on a special Blackjack table. Another kind of cards are SET, in [9] research how these SETs can automatically be detected from an image using Computer Vision, dealing with three problems sequentially: the locating of cards on the image, the classification of the cards and the finding of SETs amongst the cards. ...
Graphical abstract Abstract This paper is inspired by detection and identification of Anglo-American playing cards from an image using an entry-level webcam and Computer Vision. Some prior approaches for card recognitions have been made, but playing card recognition is an ongoing problem in image processing. Although one could think of methods which classify using the upper left and lower right corners of the card where the numbers are, this paper focusses on the novel method, without reading the card code, we count each individual symbols in the playing card. We implement this algorithm in Matlab solving two parts: the locating of card on the image obtained in controlled environment and the recognition of the cards. The recognition of playing cards is achieved through Thresholding combined with color segmentation and the counting of symbols in playing cards from one to ten and using SIFT for another playing cards.
... This strategy uses Hi-Lo counting system (Zutis & Hoey, 2009) for deciding the upcoming course of action. There is a counter in this strategy which increases one unit when the dealer draws a low card 5 and decreases one unit when the dealer draws a high card, 6 and in neutral card 7 cases the counter remains constant. ...
Communication and coordination are the main cores for reaching a constructive agreement among multi-agent systems
(MASs). Dividing the overall performance of MAS to individual agents may lead to group learning as opposed to individual
learning, which is one of the weak points of MASs. This paper proposes a recursive genetic framework for solving problems
with high dynamism. In this framework, a combination of genetic algorithm and multi-agent capabilities is utilised to
accelerate team learning and accurate credit assignment. The argumentation feature is used to accomplish agent learning
and the negotiation features of MASs are used to achieve a credit assignment. The proposed framework is quite general
and its recursive hierarchical structure could be extended. We have dedicated one special controlling module for increasing
convergence time. Due to the complexity of blackjack, we have applied it as a possible test bed to evaluate the system’s
performance. The learning rate of agents is measured as well as their credit assignment. The analysis of the obtained results
led us to believe that our robust framework with the proposed negotiation operator is a promising methodology to solve
similar problems in other areas with high dynamism.
Blackjack is a card game that usually played in casino where one or several players bet against a dealer. Each player and the dealer are given a pair of cards where both cards received by the player are facing up (known as the upcard) and the dealer has one card facing up and another facing down (known as the hole card). The rule is simple, the players must accumulate points to beat the dealer. The points of each card are the number that appears on the card, with cards like J, Q and K are counted 10 points. An A can be counted as 1 or 10 points at the player’s preference. Additional cards (maximum 5 cards) can be drawn be players and the dealer and both parties must not exceed 21 points (busting). This game can be played instinctively with luck but mathematicians had found a systematic way to increase the player’s advantage in Blackjack; which is known as card counting. There are many card counting techniques such as Hi-Low count, Hi-Opt II, Red 7, etc. In this study, we will determine whether the Hi-Low count technique will affect the winning probabilities of a player as well as the profit gained by a player in Blackjack. We simulate Blackjack for 10, 000 and 100, 000 trials in MATLAB 2018a using the Hi-Low count and compare the result against the trials without card counting. Furthermore, we will also vary the number of decks used in the trials as this to see how it affects the efficiency of card counting.
This paper is inspired by detection and identification of Anglo-American playing cards from an image using an entry-level webcam and computer vision. Some authors have been made algorithms for playing card recognition, but the solution of playing card detection and recognition is still in progress. Although one could think of methods, which classify using the upper left and lower right corners of the card where the numbers are, this paper focuses on the novel method. Without reading the card code, we counted each individual symbols in the playing card. We implemented this algorithm in Matlab solving two parts: Locating the card on the image obtained in a controlled environment, and recognizing the cards. The recognition of playing cards was achieved through thresholding combined with color segmentation and the counting of the symbols in playing cards from one to ten and using SIFT for another playing cards.
This paper presents an approach to the identification of playing cards and counting of chips in a poker game environment,
using an entry-level webcam and computer vision methodologies. Most of the previous works on playing cards identification
rely on optimal camera position and controlled environment. The presented approach is intended to suit a real and uncontrolled
environment along with its constraints. The recognition of playing cards lies on template matching, while the counting of
chips is based on colour segmentation combined with the Hough Circles Transform. With the proposed approach it is possible
to identify the cards and chips in the table correctly. The overall accuracy of the rank identification achieved is around
94%.
The slides presents some highlights from the book 'Template Matching Techniques in Computer Vision: Theory and Practice' from which you can appreciate the ideas behing the organization of the book.
This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.
We describe a novel method for simultaneously detecting faces and estimating their pose in real time. The method employs a convolutional network to map images of faces to points on a low-dimensional manifold parametrized by pose, and images of non-faces to points far away from that manifold. Given an image, detecting a face and estimating its pose is viewed as minimizing an energy function with respect to the face/non-face binary variable and the continuous pose parameters. The system is trained to minimize a loss function that drives correct combinations of labels and pose to be associated with lower energy values than incorrect ones. The system is designed to handle very large range of poses without retraining. The performance of the system was tested on three standard data sets-for frontal views, rotated faces, and profiles is comparable to previous systems that are designed to handle a single one of these data sets. We show that a system trained simuiltaneously for detection and pose estimation is more accurate on both tasks than similar systems trained for each task separately.
In this paper, we compare the performance of descriptors computed for local interest regions, as, for example, extracted by the Harris-Affine detector. Many different descriptors have been proposed in the literature. It is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context, steerable filters, PCA-SIFT, differential invariants, spin images, SIFT, complex filters, moment invariants, and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors.
The detection and recognition of objects in images is a key research topic in the computer vision community. Within this area, face recognition and interpretation has attracted increasing attention owing to the possibility of unveiling human perception mechanisms, and for the development of practical biometric systems. This book and the accompanying website, focus on template matching, a subset of object recognition techniques of wide applicability, which has proved to be particularly effective for face recognition applications. Using examples from face processing tasks throughout the book to illustrate more general object recognition approaches, examines the basics of digital image formation, highlighting points critical to the task of template matching; presents basic and advanced template matching techniques, targeting grey-level images, shapes and point sets; discusses recent pattern classification paradigms from a template matching perspective; illustrates the development of a real face recognition system; explores the use of advanced computer graphics techniques in the development of computer vision algorithms.
Template Matching Techniques in Computer Vision is primarily aimed at practitioners working on the development of systems for effective object recognition such as biometrics, robot navigation, multimedia retrieval and landmark detection. It is also of interest to graduate students undertaking studies in these areas.
A rotational invariant template matching method is proposed in this paper to enable accurate playing c ard recognition. Some prior approaches for card recogni tions have been made, but they are all unsuccessful . Character segmentation algorithms and affine transf ormation are then used in the playing card recognition system which works well for low noise images. The p roposed method is proved to be computationally effi cient and sufficiently accurate for use in card games suc h as Baccarat.
This book is the outcome of two workshops that brought together about 40 prominent vision and machine learning researchers interested in the fundamental and applicative aspects of object recognition, as well as representatives of industry. The main goals of these two workshops were (1) to promote the creation of an international object recognition community, with common datasets and evaluation procedures, (2) to map the state of the art and identify the main open problems and opportunities for synergistic research, and (3) to articulate the industrial and societal needs and opportunities for object recognition research worldwide. These goals are reflected in a relatively small number of papers that illustrate the breadth of today's object recognition research and the arsenal of techniques at its disposal, and discuss current achievements and outstanding challenges. Most of the chapters are descriptions of technical approaches, intended to capture the current state of the art. Some of the chapters are of a tutorial nature. They cover fundamental building blocks for object recognition techniques.
Hough has proposed an interesting and computationally efficient procedure for detecting lines in pictures. This paper points out that the use of angle-radius rather than slope-intercept parameters simplifies the computation further. It also shows how the method can be used for more general curve fitting, and gives alternative interpretations that explain the source of its efficiency.
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Automatic blackjack monitoring
W Cooper
K Dawson-Howe
Wesley Cooper and Kenneth Dawson-Howe. Automatic blackjack monitoring. In Proc. of Irish Machine Vision Conference, pages 248–254, 2004
