Auto Recognizing System for Dice Games

Abstract

Dice have been part of the way that humans play games for many centuries. It is probably about as long as man has been playing games at all. Six-sided dice had been developed near Rome dating back to 900 B.C.. Recently, dice are most often associated with gambling games and strategy war games; they are used dice in highly abstract ways in both. Similarly, liar dice games are a kind of interesting and popular game that can be found in almost every pub in China and Hong Kong. Nowadays, electronic gambling machines have become increasingly popular. The first such machines employing electromechanical principles were slot machines. For increasing interest, electronic gambling machines have emerged using mechanical motion of various types to produce random numbers. Typically, these kinds of games are electronic roulette and electronic dice machines. In their structure, the important module of electronic dice machines is the detection of dice location and throwing manner. Such machines are extremely attractive to users. Simultaneously, they provide results visually giving no room for fraudulently acquired numbers. Here, we propose an automated detection system with machine vision to execute such inspection. Machine vision is a powerful tool and is widely employed in automatic monitoring and detecting processes. The system employs image processing techniques, and the unsupervised algorithm to estimate the location of each die and identify the spot number accurately and effectively. The proposed algorithms are substituted for manual recognition. From the experimental results, it is found that this system is excellent due to its good capabilities which include flexibility, high speed, and high accuracy.