Automatic Recognition System for Poker Games

碩士 === 元智大學 === 資訊工程學系 === 96 === Since technology are developed quickly and fetch image equipment (digit camera, webcam ,etc.) are cost reduced, the application of digital image are more extensive. In the computer image field, image recognition has been developed for years, and it applies to many s...

Full description

Bibliographic Details
Main Authors: Chia-Hsuan Cheng, 鄭珈炫
Other Authors: 林啟芳
Format: Others
Language:zh-TW
Published: 2007
Online Access:http://ndltd.ncl.edu.tw/handle/75025836689306651265
Description
Summary:碩士 === 元智大學 === 資訊工程學系 === 96 === Since technology are developed quickly and fetch image equipment (digit camera, webcam ,etc.) are cost reduced, the application of digital image are more extensive. In the computer image field, image recognition has been developed for years, and it applies to many situation such as characters recognition, palm line recognition, cards recognition, license plate recognition, face recognition ,etc. They created a lot of research results. The method utilizing vision of the computer without artificial operation offers diversified services. This paper is mainly to design a real time poker recognition system. Put poker on the tabletop arbitrarily, fetch the image on the tabletop with the webcam, and deliver it to computer for real-time recognition. No matter the angle that card put, the system can recognize the produce design of poker. It mainly includes cutting, calculating the quantity of design, designing recognition, JQK recognition etc. Based on detection, the algorithm of performing recognition the design is mainly to describe the characteristic of the object. The characteristic wave form of the design won can be subsequently obtained. We cut the unsmooth area in the characteristic wave form out and utilize unsmooth difference recognition design. The proposed method can deal with each objects edge outline characteristic value without considering the object angle. It shows good results in resistance to the displacement, rotation and distance of the image. And the value does not change. Moreover, there are good result of recognition of the object with different size. Although JQK image is very complicated, it is the characteristic of utilizing the image head area to recognition the card of these three kinds after analysis. We can recognize the image of this area clearly and can reduce the complexity and computational speed.