猜拳機

Finger-Guessing Game

曹文潔(Wen-Jie Cao)

指導教授 ： 王文俊

國立中央大學/資訊電機學院/電機工程學系/碩士(2007年)

摘要

本論文以程式及多媒體應用技術設計製作完成一個電腦與人互動的猜拳遊戲機。我們利用一台網路攝影機及電腦，搭配由程式所撰寫出的介面，製作成猜拳遊戲。由電腦隨機亂數所產生的拳數，與真人所出拳數來判斷輸贏之結果，再採用音樂及動畫來使遊戲更為生動。真人拳數的判定，是利用影像處理之技術，先以網路攝影機拍攝真人手勢，再作背景相減，來去除背景中類似膚色的物品；膚色偵測，偵測出手的位置及區域；雜訊去除，消除不必要的影像資訊，最後，再利用手的特性，來分析所得的影像資料，判定手勢為何種拳數。為了達到人與電腦猜拳的真實性與刺激性，真人出拳與電腦出拳必須同步，辨識真人手勢與判決輸贏必須即時，又為了增加趣味性，因此，我們設定一機制：在遊戲過程中，播放音樂作為出拳節奏，在音樂尚未結束，不執行任何手勢辨識；音樂結束後，同時做辨識真人出拳手勢，並與電腦隨機產生之出拳手勢，來判定輸贏，再以輸贏結果，選擇相對應之音效，顯示於介面上。本作品雖屬娛樂性質，但其包含多種實用技術如手勢辨識、多媒體電腦介面製作等，應可應用於其他實用方面的用途，譬如：手語手勢辨識、電腦視覺等等，更增加了本研究的實用價值。

關鍵字

手勢辨識 ； 影像處理

並列摘要

This thesis designs a finger-guessing game for two players, human and PC, under Microsoft Windows environment. This game is implemented by using C++ language and multimedia techniques. A webcam and a PC are used to construct a human interactive interface for the game system. In the process of the game, the webcam catches the hand image of the human and then the PC recognizes the hand gesture real time in streaming videos acquired from the webcam. At the same time, the PC produces three different finger-gestures, including paper, scissors and stone, randomly. Then, the PC judges the winner between the human or PC. In order to increase the interest, the game collocates playing music, sound effect, and moving patterns, etc..
The proposed system is divided into three main modules, gesture recognition module, synchronic module, and judgment module. The gesture recognition module contains color model transformation, background subtraction, hand detection, and finger-gesture identification. The synchronic module guarantees the show time of two players’ hands is simultaneous and synchronal. Finally, the judgment module judges that who is the winner and plays some sound effect for the winner or the loser. Although this work is an entertainment game, it contains many practical techniques in image processing, pattern recognition, and multimedia applications, etc.. These techniques can be apply to other applications such as, the sign language or gesture recognition, and computer vision applications, etc..

並列關鍵字

image processing ； gesture recognition

參考文獻

[1] J. Kuch, “Vision-based hand modeling and gesture recognition for human computer interaction,” M.S. Thesis, Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, 1994.

[2] J. Segen and S. Kumar, “Fast and accurate 3D gesture recognition interface,” in Proc. IEEE International Conference Automatic Face and Gesture Recognition, 1998.

[3] C. C. Chang, I. Y. Chen, and Y. S. Huang, “Hand pose recognition using curvature scale space,” in Proc. 16th International Conference on Pattern Recognition, pp. 386-389, 2002.

[4] Y. L. Ma, F. Pollick, and W. T. Hewitt, “Using B-spline curves for hand recognition,” in Proc. 17th International Conference on Pattern Recognition, pp. 274-277, 2004.

[5] X. Liu and K. Fujimura, “Hand gesture recognition using depth data,” in Proc. 6th IEEE International Conference on Automatic Face and Gesture Recognition, pp. 529-534, 2004.