本研究以開發一個即時辨識手勢系統為目的。以新興的Intel® RealSense 3D相機技術並結合支持向量機器(Support vector machine)來做資料分類達到即時辨識手勢。
在現今的科技發展手勢操作在各項產業中扮演著不可或缺的角色，其中在智慧型手機、平板電腦、個人電腦、筆記型電腦、電視等，都可能在未來的發展中置入具有深度學習功能的智慧型相機，並藉由手勢控制改變目前的人機互動體驗，因此本研究藉由Intel® RealSense 3D相機來探討手勢辨識研究。
本研究以Intel® RealSense 3D相機擷取手部關節點，擷取的手部關節點為22個含有世界三維座標的深度點，並藉由台灣大學林智仁教授所開發的LIBSVM將所擷取的手部關節點做訓練產生手勢模型，接下來將Intel® RealSense 3D相機擷取的手部關節點導入由LIBSVM生成的手勢模型做比較即可得到分類結果
使用本研究所開發的人機介面程式，可以辨識10種數字手勢且平均辨識率達99.5%，並將11個英文字母手勢應用於手勢打字，以驗證本研究之正確性。

Gestures control technology is becoming more advanced. In the future, smart phones, Tablet, personal computers, laptops, TVs, etc., will utilize smart cameras with deep learning capabilities to recognize gestures. Using gesture control changes the human-computer interaction experience, so this study explored gesture recognition using Intel® RealSense 3D cameras, and the goal is to develop a Real-Time Recognition of Static Hand Gesture system.
The data for the recognition gestures is classified by using Intel® RealSense 3D camera technology combined with Support Vector Machine. In this study, hand joints were imported using Intel® RealSense 3D camera. The extracted 22 hand joints includes the world's three-dimensional coordinates using LIBSVM developed by Professor Lin of Taiwan University, and the extracted hand joints are trained to generate a gesture model. The gesture taken by the Intel® RealSense 3D camera are compared to the LIBSVM generated gesture model to receive a classification result.
After implementing the human-computer program developed in this study, on average of 99.5% of numeric gestures were correctly identified, and 11 alphabets were recognized to conduct gesture typing.

參考文獻
[1] P. N. Belhumeur, J. Hespanha, and D. J. Kriegman, "Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 711-720, 1997.
[2] J. Davis and M. Shah, "Visual gesture recognition," Proc. of IEE on Vision, Image and Signal Processing, vol. 141, pp. 101-106, 1994.
[3] W. Du and H. Li, "Vision based gesture recognition system with single camera," Proc. of ICSP2000, vol. 2, pp. 1351-1357, 2000.
[4] 沈全發, "機械式手套與虛擬實境之整合研究," 國立成功大學，碩士論文, 2002.
[5] 葉政憲, "手部資訊擷取系統之設計與應用," 國立成功大學，碩士論文, 2005.
[6] C. L. Huang and S. H. Jeng, "A model-based hand gesture recognition system," Machine Vision and Applications, vol. 12, no. 5, pp. 243-258, 2001.
[7] T. S. Huang, Y. Wu, and J. Lin, "3D model-based visual hand tracking," Proc. of the 2002 IEEE Int. Conf. on Multimedia and Expo, vol. 1, pp. 905-908, 2002.
[8] Y. Yasumuro, Q. Chen, and K. Chihara, "3D modeling of human hand with motion constraints," Proc. of the Int. Conf. on 3-D Digital Imaging and Modeling, pp. 275-282, 1997.
[9] J. Lee and T. L. Kunii, "Model-based analysis of hand posture," IEEE Computer Graphics and Applications, vol. 1, no. 5, pp. 77-86, 1995.
[10] C. C. Lien and C. L. Huang, "Model-based articulated hand motion tracking for gesture recognition," Image and Vision Computing, vol. 16, no. 2, pp. 121-134, 1998.
[11] C. C. Lien and C. L. Huang, "The model based dynamic hand posture identification using genetic algorithm," Machine Vision and Applications, vol. 11, pp. 107-121, 1999.
[12] Y. Wu and T. S. Huang, "Capturing articulated human hand motion: A divide-and-conquer approach," Proc. of IEEE Int. Conf. on Computer Vision, pp. 606-611, 1999.
[13] F. Lathuiliere and J. Y. Herve, "Visual tracking of hand posture with occlusion handling " Proc. of the 15th Int. Conf. on Pattern Recognition, vol. 3, pp. 1129-1133, 2000.
[14] S. Y. Ho, Z. B. Huang, and S. J. Ho, "An evolutionary approach for pose determination and interpretation of occluded articulated objects," Proc. of the 2002 Congress on Evolutionary Computation, vol. 2, pp. 1092-1097, 2002.
[15] J. M. Rehg and T. Kanade, "Model-based tracking of self-occluding articulated objects," Proc. of the 5th Int. Conf. on Computer Vision, pp. 612-617, 1995.
[16] T. Heap and D. Hogg, "Towards 3D hand tracking using a deformable model," Proc. of the 2nd Int. Conf. on Automatic Face and Gesture Recognition, pp. 140-145, 1996.
[17] 陳治宇, "虛擬滑鼠：以視覺為基礎之手勢辨識," 國立中山大學，碩士論文, 2011.
[18] 莊義宗, "應用隱藏式馬可夫模式於靜態手勢辨識," 大同大學，碩士論文, 2013.
[19] L. R. Rabiner, "A tutorial on hidden markov models and selected applications in speech recognition," Proceedings of the IEEE, vol. 77, no. 2, pp. 257 - 286, 1989.
[20] 王建中, "鑑別性隱藏式馬可夫模型應用於人臉辨識," 國立成功大學，碩士論文, 2005.
[21] 江明晏, "耦合隱藏式馬可夫模型於雙手手勢辨識," 國立成功大學，碩士論文, 2007.
[22] A. Corradini, "A Real-time gesture recognition by means of hybrid recognizers," Human-Computer Interaction, pp. 34-46, 2002.
[23] R. H. Liang and M. Ouhyoung, "A real-time continuous gesture recognition system for sign language," IEEE Conf. on Automatic Face and Gesture Recognition, pp. 558-567, 1998.
[24] Q. Chen, N. D. Georganas, and E. M. Petriu, "Hand gesture recognition using haar-like features and a stochastic context-free grammar," IEEE Transactions on Instrumentation and Measurement, vol. 57, no. 8, pp. 1562-1571, 2008.
[25] 李健銘, "即時手語辨識," 國立成功大學，碩士論文, 2010.
[26] 劉書銘, "以深度資訊為基礎的寬鬆靜態手勢辨識," 國立中央大學，碩士論文, 2013.
[27] K. K. Biswas and S. K. Basu, "Gesture recognition using Microsoft Kinect," Proc. of the 5th Int. Conf. on Automation, Robotics and Applications, pp. 100-103, 2011.
[28] "Human Computer Interaction : KINECT Sensor," http://www.cs.nccu.edu.tw/~whliao/hci2012/moe-hci-B41-kinect.pptx.
[29] Intel, "Intel® RealSense™ SDK 2016 R3 Documentation," https://software.intel.com/sites/landingpage/realsense/camera-sdk/v2016r3/documentation/html/index.html?doc_devguide_introduction.html.
[30] 李俊明, "雙影像多視角結構光轉三維點資料技術發展," 國立中央大學，碩士論文, 2016.
[31] R. Mangera, "Static gesture recognition using features extracted," Council of Scientific and Industrial Research, 2013.
[32] C. Wang, Z. Lin, and S. C. Chan, "Superpixel-Based hand gesture recognition with Kinect depth camera," IEEE Transactions on Multimedia, vol. 17, no. 1, pp. 29-39, 2015.
[33] C. F. Wu, J. Xie, and L. Yu, "Research and application of gesture recognition based on information of body skeleton and depth," Computer Technology and Development, vol. 26, no. 8, pp. 200-204, 2016.
[34] H. B. Lee, Y. YU, and Y. Chen, "Static gesture recognition method via using RealSense depth information," http://www.paper.edu.cn/releasepaper/content/201703-285, 2017.
[35] N. H. Dardas and N. D. Georganas, "Real-time hand gesture detection and recognition using bag-of-features and support vector machine techniques," IEEE Transactions on Instrumentation and Measurement, vol. 60, no. 11, pp. 3592-3607, 2011.
[36] C. Cortes and V. Vapnik, "Support-Vector Networks," Machine Learning, vol. 20, pp. 273-297, 1995.
[37] "支援向量機," https://zh.wikipedia.org/wiki/%E6%94%AF%E6%8C%81%E5%90%91%E9%87%8F%E6%9C%BA.
[38] 林宗勳, "Support Vector Machines 簡介," http://www.cmlab.csie.ntu.edu.tw/~cyy/learning/tutorials/SVM2.pdf.
[39] C. W. Hsu, C. C. Chang, and C. J. Lin, "A practical guide to Support Vector Classification," https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf, 2016.
[40] C. C. Chang and C. J. Lin, "LIBSVM: A Library for Support Vector Machines," National Taiwan University, 2013.
[41] "美國手語字母," https://zh.wikipedia.org/wiki/%E7%BE%8E%E5%9C%8B%E6%89%8B%E8%AA%9E%E5%AD%97%E6%AF%8D.