基於機器學習的無線空中手寫識別系統｜國立清華大學博碩士論文庫

簡易檢索 / 詳目顯示

回結果列表

研究生：	林倬安 Lin, Cho-An.
論文名稱：	基於機器學習的無線空中手寫識別系統 A Wireless In-Air Handwriting Recognition System Based on Machine Learning
指導教授：	周百祥 CHOU, PAI-HSIANG 周志遠 CHOU, JERRY
口試委員:	蔡明哲 TSAI, MING-JER 韓永楷 HON, WING KAI
學位類別：	碩士 Master
系所名稱：
論文出版年：	2017
畢業學年度：	105
語文別：	英文
論文頁數：	45
中文關鍵詞：	機器學習、手勢辨識、嵌入式系統
外文關鍵詞：	machine learning, gesture recognition, embedded system
相關次數：	點閱：1 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

本文提出一個以動作感測為主的穿戴式手指空中手寫辨識系統。我們主要將貼附在手指環上微小的慣性感測器收集到的資訊，透過藍芽傳送到電腦端進行資料處理。處理的方
式為特徵提取，最後透過基於支持向量機(SVM)的機器學習，辨認使用者的手寫字母。實驗結果顯示，在辨識Grafﬁti字母集上，我們的演算法能夠達到相當高的準確性：個人化可達96%，而一般辨識則可達91%的正確率。

We propose a ﬁnger-wearable motion sensing system for handwriting recognition in the air. The hardware consists of a miniature inertial measurement unit (IMU) on a ring with a Bluetooth Low Energy (BLE) transceiver to a computer that then performs feature extractions and classiﬁcation based on support vector machine (SVM) to recognize the written characters. We tested our system on Grafﬁti alphabet, and experimental results show a recognition rate of 96% and 91% on user-dependent and user-independent recognition, respectively.

Contents i
Acknowledgments vi
Introduction 1
1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
2 Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
3 Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
4 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
Related Work 4
1 Movement-based recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2 Vision-based Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
Background 6
1 K-nearest neighbors algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2 Decision Tree . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
3 Naive Bayes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
4 Logistic Regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
Recognition Method 9
1 Motion Sensing System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2 Recognition Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.1 Vector Conversion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.2 Trajectory Repair . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
2.3 Normalization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3 Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4 Support Vector Machine . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
4.1 Optimal Hyperplane . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
4.2 Non-linear classiﬁcation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
Evaluation 25
1 Gesture Vocabulary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
2 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
2.1 Experimental environment . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
2.2 Experimental Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
3 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
3.1 Recognition Accuracy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
3.2 Run-Time Complexity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
3.3 Discussion and Compare . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
Conclusions and Future Work 36
1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
2.1 Gesture Segment Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . 37
2.2 Conversion Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
Appendix 38
Main Source Code . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
                                

[1] J. ao Gabriel Abreu, J. ao Marcelo Teixeira, L. S. Figueiredo, and V. Teichrieb, “Evaluating sign
language recognition using the Myo armband,” in Virtual and Augmented Reality (SVR), 2016
XVIII Symposium on, pp. 64–70, IEEE, 2016.
[2] M. Mohandes, M. Deriche, and J. Liu, “Image-based and sensor-based approaches to Arabic
Sign Language recognition,” IEEE Transactions on Human-Machine Systems, vol. 44, no. 4,
pp. 551–557, 2014.
[3] K. K. Biswas and S. K. Basu, “Gesture recognition using Microsoft Kinect®,” in Automation,
Robotics and Applications (ICARA), pp. 100–103, IEEE, 2011.
[4] R. Aggarwal, S. Swetha, A. Namboodiri, J. Sivaswamy, and C. Jawahar, “Online handwriting
recognition using depth sensors,” in Document Analysis and Recognition (ICDAR), pp. 1061–
1065, IEEE, 2015.
[5] J. Kim, S. Mastnik, and E. André, “EMG-based hand gesture recognition for realtime biosignal
interfacing,” in Proceedings of the 13th international conference on Intelligent user interfaces,
pp. 30–39, ACM, 2008.
[6] C. Xu, P. H. Pathak, and P. Mohapatra, “Finger-writing with smartwatch: A case for ﬁnger and
hand gesture recognition using smartwatch,” in Proceedings of the 16th International Workshop
on Mobile Computing Systems and Applications, pp. 9–14, ACM, 2015.
[7] J. Luan, T.-C. Chien, S. Lee, and P. H. Chou, “HANDIO: A wireless hand gesture recognizer
based on muscle-tension and inertial sensing,” in Global Communications Conference (GLOBE-
COM), IEEE, 2015.
[8] S. Zhang, C. Yuan, and Y. Zhang, “Handwritten character recognition using orientation quantiza-
tion based on 3D accelerometer,” in Proceedings of the 5th Annual International Conference on
Mobile and Ubiquitous Systems: Computing, Networking, and Services, pp. 54:1–54:6, ACM,
2008.
[9] R. Xu, S. Zhou, and W. J. Li, “MEMS accelerometer based nonspeciﬁc-user hand gesture recog-
nition,” IEEE Sensors Journal, vol. 12, no. 5, pp. 1166–1173, 2012.
[10] Y.-Z. Xie, “String matching algorithm for real-time hand gesture recognition on a wireless low-
power embedded device,” Master’s thesis, 2016.
[11] S. Zhou, Z. Dong, W. J. Li, and C. P. Kwong, “Hand-written character recognition using MEMS
motion sensing technology,” in 2008 IEEE/ASME International Conference on Advanced Intel-
ligent Mechatronics, pp. 1418–1423, IEEE, 2008.
[12] G. Katiyar and S. Mehfuz, “MLPNN based handwritten character recognition using combined
feature extraction,” in International Conference on Computing, Communication Automation,
pp. 1155–1159, IEEE, 2015.
[13] D. Nasien, H. Haron, and S. S. Yuhaniz, “Support Vector Machine (SVM) for English handwrit-
ten character recognition,” in 2010 Second International Conference on Computer Engineering
and Applications, vol. 1, pp. 249–252, IEEE, 2010.
[14] M. E. W. Putra and I. Supriana, “Structural ofﬂine handwriting character recognition using Lev-
enshtein distance,” in 2015 International Conference on Electrical Engineering and Informatics
(ICEEI), pp. 31–36, IEEE, 2015.
[15] L. Rokach and O. Maimon, “Top-down induction of decision trees classiﬁers–a survey,” IEEE
Transactions on Systems, Man, and Cybernetics, Part C, vol. 35, pp. 476 – 487, October 2005.
[16] “CC2541 advanced remote control reference design.” http://www.ti.com/tool/cc2541arc-rd.
[17] G. Hackeling, Mastering Machine Learning with scikit-learn. 2014.
[18] W. Deng, J. Hu, J. Lu, and J. Guo, “Transform-invariant PCA: A uniﬁed approach to fully auto-
matic FaceAlignment, representation, and recognition,” IEEE Transactions on Pattern Analysis
and Machine Intelligence, vol. 36, pp. 1275–1284, June 2014.
48[19] R. Yasir and R. A. Khan, “Two-handed hand gesture recognition for Bangla sign language using
LDA and ANN,” in Software, Knowledge, Information Management and Applications (SKIMA),
2014 8th International Conference on, IEEE, April 2015.
[20] V. N. Vapnik, The Nature of Statistical Learning Theory. 1999.
[21] C. H. Blickenstorfer, “Grafﬁti: Wow!,” Pen Computing Magazine, 1995.
[22] I. S. MacKenzie and S. X. Zhang, “The immediate usability of Grafﬁti,” in Proceedings of the
conference on Graphics interface ’97, pp. 129–137, ACM, 1997.
[23] H. Tinwala and I. S. MacKenzie, “Eyes-free text entry on a touchscreen phone,” in Proceedings
of the (IEEE) Toronto International Conference Science and Techonology for Humanity, pp. 83–
89, 2009.
[24] “Python interface to Bluetooth LE on Linux.” https://github.com/IanHarvey/bluepy.
[25] R. Darbar and D. Samanta, “Magitext: Around device magnetic interaction for 3d space text
entry in smartphone,” in 2015 IEEE International Conference on Electronics, Computing and
Communication Technologies (CONECCT), pp. 1–4, July 2015.
[26] O. F. Özer, O. Özün, C. O. Tüzel, V. Atalay, and A. E. Çetin, “Vision-based single-stroke char-
acter recognition for wearable computing,” IEEE Intelligent Systems, pp. 33–37, May 2001.

簡易檢索 / 詳目顯示

相關論文