臺灣博碩士論文加值系統

利用手勢辨識可協助無人看護或行動不便人士等對周遭設備(如電腦和電器)的操作。本論文針對連續手勢提出一套辨識方法。利用顏色的屬性追蹤手勢及做出手勢切割。先以Central Moments的方法求得特徵向量，再利用隱藏式馬可夫模型進行複雜背景下一至多種手勢的辨識。本論文所提方法，可使電腦具有更便利、省人工和人性化之辨識方法。

People with disabilities can operate Machines and Computers with the help of hand gesture recognition. This thesis proposed a method for hand gesture recognition. Detecting and segmentation human hand are finished by the color attribute. We use Central Moments as the shape feature, and recognize gesture under complex environment through hidden markov model. The method we proposed make users interact with machines more convenient, humanistic and easily.

摘要 i
ABSTRACT ii
誌謝 iii
目錄 iv
圖目錄 vii
表目錄 ix
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 1
1.3 研究範圍與限制 2
1.4 論文架構 3
第二章 相關技術與文獻討論 4
2.1 手勢辨識相關技術討論 4
2.2影像式手勢辨識相關技術討論 5
2.3模型式手勢辨識相關技術討論 7
第三章系統架構 9
3.1 手勢辨識系統 9
3.2 手勢辨識系統架構 9
第四章 物件追蹤與切割 12
4.1 物件追蹤 12
4.1.1核心函數(Kernel Function) 12
4.1.2移動物體影像之色彩分佈密度函數 13
4.1.3移動物體候選影像之色彩分佈密度函數 14
4.1.3 Bhattacharyya Coefficient 15
4.2 MEAN SHIFT 18
4.2.1 Mean Shift Vector 18
4.2.2 Mean Shift之實作流程 20
4.3 PARTICLE FILTER 21
4.3.1 Particle Filter模型 21
4.3.2 Particle Filter相關參數 23
4.3.3 Particle Filter之實作流程 25
4.4 MEAN SHIFT 與 PARTICLE FILTER結合 26
4.5 物件切割 29
4.5.1 膚色偵測 29
4.5.2 雜訊移除 33
第五章 手勢特徵擷取 35
5.1 手形擷取 35
5.1.1 Central Moments 35
5.2 向量量化 37
5.2.1 向量量化的觀念 37
第六章 手勢訓練與辨識 39
6.1 隱藏式馬可夫模型 39
6.1.1 隱藏式馬可夫模型的種類 39
6.1.2 隱藏式馬可夫模型的參數 42
6.2 應用隱藏式馬可夫模型做辨識 43
6.2.1輸出機率的計算 43
6.2.2 Forward Procedure 44
6.2.3 Backward Procedure 45
6.2.4 Viterbi 演算法 46
6.3 隱藏式馬可夫模型的訓練 48
6.3.1 Baum Welch 演算法 48
6.3.2 多個觀測序列的參數估計 50
第七章 實驗結果與分析 51
7.1 實驗分析資料 51
7.2 實驗結果與討論 54
第八章 結論與未來展望 59
8.1 結論 59
8.2未來展望 59
參考文獻 61

[1].K. Abe, H. Saito, and S. Ozawa, “Virtual 3-D interface system via hand motion recognition from two cameras,” IEEE Trans. on Systems, Man, and Cybernetics-Part A, Vol.32, No.4, pp.536-540, July 2002.
[2].M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, “A tutorial on particle filters for online nolinear/non-gaussian Bayesian tracking,” IEEE Trans. on Signal Processing, pp. 174-188, Vol. 50, No. 2, 2002.
[3].V. Athitsos and S. Sclaroff, “An appearance-based framework for 3D hand shape classification and camera viewpoint estimation,” Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, pp. 45-50, 2002.
[4].V. Athitsos and S. Sclaroff, “Estimating 3D Hand Pose from a Cluttered Image,” Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 432-439, Vol. 2, 2003.
[5].M. Bray, E. Koller-Meier, and L. Van Gool, “Smart particle filtering for 3D hand tracking,” Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, pp. 675-680, 2004.
[6].D. Comaniciu, V. Ramesh, and P. Meer, “Real-time tracking of non-rigid objects using mean shift,” Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 142-149, 2000.
[7].B. Han, D. Comaniciu, Y. Zhu, and L. Davis, “Incremental density approximation and kernel-based Bayesian filtering for object tracking,” Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 638-644, Vol. 1, 2004.
[8].M. Isard and A. Blake, “CONDENSATION-conditional density propagation for visual tracking,” Int. J. of Computer Vision, pp. 5-28, Vol. 29, No. 1, 1998.
[9].M. Isard and A. Blake, “ICONDENSATION: unifying low-level and high-level tracking in a stochastic framework,” Proc. European Conf. Computer Vision, pp.893-908, 1998.
[10].J. Y. Lin, Y. Wu, and T. S. Huang, “3D model-based hand tracking using stochastic direct search method,” Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, pp. 693-698, 2004.
[11].S. Lu, D. Metaxas, D. Samaras, and J. Oliensis, “Using multiple cues for hand tracking and model refinement,” Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 443-450, Vol. 2, 2003.
[12].K. Oka, Y. Sato, and H. Koike, “Real-time fingertip tracking and gesture recognition,” IEEE Computer Graphics & Applications, Vol. 22, No. 6, Nov. 2002.
[13].V. I. Pavlovic, R. Sharma, and T. S. Huang, “Visual interpretation of hand gestures for human-computer interaction: A review,” IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 677-695, Vol. 19, No. 7, July 1997.
[14].R. Rosales, V. Athitsos, L. Sigal, and S. Sclaroff, “3D hand pose reconstruction using specialized mappings,” Proc. IEEE Int. Conf. Computer Vision, pp. 378-385, Vol. 1, 2001.
[15].Y. Rui and Y. Chen, “Better proposal distributions: object tracking using unscented particle filter,” Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 786-793, Vol. 2, 2001.

[16].C. Shan, Y. Wei, T. Tan, and F. Ojardias, “Real time hand tracking by combining particle filtering and mean shift,” Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, pp. 669-674, 2004.
[17].N. Shimada, K. Kimura, and Y. Shirai, “Real-time 3-D hand posture estimation based on 2-D appearance retrieval using monocular camera,” Proc. Int. Workshop RATFG-RTS, pp. 23-30, 2001.
[18].B. Stenger, P. R. S. Mendonca, and R. Cipolla, “Model-based 3D tracking of an articulated hand,” Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 310-315, Vol. 2, 2001.
[19].B. Stenger, A. Thayananthan, P. H. S. Torr, and R. Cipolla, “Filtering using a tree-based estimator,” Proc. IEEE Int. Conf. Computer Vision, pp. 1063-1070, Vol. 2, 2003.
[20].C. Tomasi, S. Petrov, and A. Sastry, “3D tracking = classification + interpolation,” Proc. IEEE Int. Conf. Computer Vision, 2003.
[21].J. Triesch and C. von der Malsurg, “A system for person-independent hand posture recognition against complex background,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 23, No. 12, Dec. 2001.
[22].A. Utsumi and J. Ohya, “Multiple-hand-gesture tracking using multiple cameras,” Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 473-478, Vol. 1, 1999.
[23].Y. Wu and T. S. Huang, “Capturing articulated human motion: a divide-and-conquer approach,” Proc. IEEE Int. Conf. Computer Vision, pp. 606-611, 1999.
[24].Y. Wu, J. Y. Lin, and T. S. Huang, “Capturing natural hand articulation,” Proc. IEEE Int. Conf. Computer Vision, pp. 426-432, Vol. 2, 2001.

[25].M. Yamamoto, T. Watanabe, and K. Osaki, “Development of an embodied interaction system with InterActor by speech and hand motion input,” IEEE Int. Workshop Robot and Human Interactive Communication, pp. 323–328, 2005
[26].N. K. Looi, C. K. Loo, K. N. Pau, “Real time actions and gestures as intuitive user interface for creative 3D modeling,” Proc. Int. Conf. Active Media Technology, pp. 487–490, 2005
[27].L. Devroye, L. Gyorfi and G. Lugosi, “A Probabilistic Theory of Pattern Recognition,” Applications of Mathematics. Springer-Verlag Inc., Vol. 31, pp. 25-32, 1996.
[28].R. L. Hsu, M. A. Mottaleb, and A. K. Jain, “Face detection in color images,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 24, Issue 5, pp. 696 – 706, 2002
[29].M. K. Hu, “Visual pattern recognition by moment invariants,”IEEE Trans. on Information Theory, Vol. 8, Issue 2, pp. 179 – 187, 1962
[30].K. Okuma, A. Taleghani, N. de Freitas, J. J. Little, andD. G. Lowe, “A boosted particle filter: Multitarget detectionand tracking,” European Conference on Computer Vision , Vol. 1, pp. 28 – 39, 2004.
[31].Cheng Chang, R. Ansari, and A. Khokhar. “Multiple object tracking with kernel particle filter,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition., Vol. 1, pp. 566 – 573, 2005.