隨著電腦科技的進步，人機互動的改進一直是許多發表研究所專注的課題，從早期的鍵盤，滑鼠，到現在的攝影機，手寫筆、板等。都是為了能讓使用者能夠更方便地操作電腦。其演變趨勢從以機器為主，即使用者要學習如何操作電腦，轉變為以人為主，即由電腦配合人的習慣，讓使用者可以以自己的經驗習慣操作電腦。
本論文中提出了一套手勢辨識系統，可以在已知的環境底下去做手勢辨識，目的在於發展為一種新的人機互動機制，使用者僅須對攝影機比出已定義過的手勢，即可對電腦下命令。此方法不需要使用者戴手套或在指尖上塗顏色或安裝標誌即可辨識。其方法主要是以色彩資訊為基準，以HSI色彩空間為主，形態學的增長為輔找出手部區域及輪廓，並使用指尖模型找出指尖位置，利用所取得的資訊及連續影像的特性來預測指尖位置並追蹤之，最後經由追蹤到的結果來判斷使用者的手勢。

With the increasing advancing of pervasive computer and information technology, human-computer interaction has become a major research and development topic. The goal of this study is to involve human-computer interaction for ubiquitous interactions so as to provide a friendly service for users and to alleviate the burden of typing in keyboard and writing in tablet. In other words, the proposed method tries to recognize hand gesture, which in turn to provide a comfortable, attentive, and reliable system for human-computer interface.
The proposed method consists of three phases: hand detection, fingertip tracing, and hand gesture recognition. In the stage of hand detection, skin-color information is used to detect the hand silhouette. In the stage of fingertip tracing, the edge detection and fingertip mask are involved to extract the fingertip trajectory. Finally, in the stage of hand gesture recognition, the fingertip trajectory vectors are extracted and matching strategy is adopted to achieve the goal of recognition. The effectiveness and practicability of the proposed method have been demonstrated by various experiments.

摘要 ............................................ii
Abstract .......................................iii
誌謝 ............................................iv
目錄 .............................................v
圖目錄 .........................................vii
表目錄 ..........................................ix
第一章 序論 ...................................1
1.1 研究背景與動機 ...........................1
1.2 問題描述 ...........................2
1.3 相關研究 ...........................3
1.4 系統流程 ...........................5
1.5 論文架構 ...........................7
第二章 手部區域切割 ...........................9
2.1 手勢影像擷取 ...........................9
2.2 色彩空間RGB轉HSI ...................9
2.3 形態學 ..................................11
2.4 輪廓擷取 ..........................13
第三章 指尖軌跡追蹤 ..........................17
3.1 指尖追蹤流程 ..........................17
3.2 指尖初始位置估計 ..................18
3.3 指尖位置擷取 ..........................20
3.4 指尖位置預測與追蹤 ..................23
第四章 手勢辨識 ..........................25
4.1 手勢辨識流程 ..........................25
4.2 簡化指尖運動軌跡 ..................26
4.3 抓取手勢特徵點 ..........................26
4.4 計算與累加同一方向手勢特徵方向值 ..28
4.5 手勢正規化描述與手勢辨識 ..........30
第五章 實驗與測試結果 ..........................32
5.1 實驗環境與設備 ..........................32
5.2 實驗影像與結果 ..........................32
5.3 辨識錯誤的手勢分析 ..................37
5.4 實驗結果 ..........................40
第六章 結論與未來研究 ..........................42
6.1 結論 ..................................42
6.2 未來研究 ..........................42
參考文獻 ..................................44

[1]C. N?匜ker and H. Ritter, “Visual recognition of continuous hand postures,” IEEE Transaction on Neural Networks, vol. 13, no. 4, pp. 983-994, 2002.
[2]H. Koike, K. Oka, and Y. Sato, “Real-time fingertip tracking and gesture recognition,” IEEE Computer Graphics and Applications, vol. 22, pp. 64-71, 2002.
[3]L. Kakadiaris and D. Metaxas, “Model-based estimation of 3D human motion,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, pp. 1453-1459, 2000.
[4]M.H. Yang, N. Ahuja, and M. Tabb, “Extraction of 2D motion trajectories and its application to hand gesture recognition,” IEEE, Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp.1061-1074, 2002.
[5]H. Guan, C.S. Chua, and Y.K. Ho, “3D hand pose retrieval from a single 2D image,” Proceedings International Conference, Image Processing, vol. 1, pp. 157-160, 2001.
[6]C. Vogler and D. Metaxas, “A framework for recognizing the simultaneous aspects of American sign language,” Computer Vision and Image Understanding, vol. 81, pp. 358-384, 2001, available online at http://www.idealibrary.com.
[7]J. Davis and M. Shah, “Visual gesture recognition,” IEE Vision, Image and Signal Processing, vol. 141, pp. 101-106, 1994.
[8]T.C .Terrillon, T. Pilpre, Y. Niwa, and T. Yamamoto, “Robust face detection and hand posture recognition in color images for human-machine interaction,” Proceedings 16th International Conference, Pattern Recognition, vol. 1, pp. 204-209, 2002.
[9]J. Triesch and C. von der Malsburg, “A system for person-independent hand posture recognition against complex backgrounds,” IEEE transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 12, pp. 1449-1453, 2001.
[10]J. Lee and T.L. Kunii, “Model-Based Analysis of Hand Posture,” IEEE Computer Graphics and Application, pp. 77-86, 1995.
[11]J. Cui and Z. Sun, “Visual Hand Motion Capture for Guiding A Dexterous Hand,” Proceedings Sixth IEEE International Conference, Automatic Face and Gesture Recognition, pp. 729-734, 2004.
[12]Y. Hanada, N. Shimada, and Y. Shirai, “Hand shape estimation under complex backgrounds for sign language recognition,” Proceedings Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004.
[13]X. Zhu, J. Yang, and A. Waibel, “Segmenting hands of arbitrary color,” Proceedings Fourth IEEE International Conference Automatic Face and Gesture Recognition, pp. 446-453, 2000.
[14]J.W. Hsieh, S.L. Yu, and Y.S. Chen, “Motion-based video retrieval by trajectory matching,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 16, no. 3, pp. 396-409, 2006.