人機互動是現今科技發展很重要的一環，好的人機互動方式往往能增加使用者的目光與接受度，在眾多人機互動方式裡以手勢來控制裝置是目前發展的趨勢之一，因為手勢對人類來說是較直覺與簡單的表達方式，有鑑於此本論文目標是發展一個能辨識數字0到9手勢的手勢辨識系統，以作為人機互動的方式。
　　本系統手勢提取不像許多文獻直接以膚色偵測抓取手勢，而是加入移動物件偵測做處理，這樣的方式能濾除很多不必要的雜訊以適應較複雜的背景。辨識手勢的部分是先進行手指指尖定位，做法是以粒子隨機擴散讓粒子分佈於手勢邊緣，接著刪除不在指尖上的粒子，而剩下的粒子再進行分群以區分不同手指上的粒子，分群後每一群粒子的平均位置即為手勢指尖定位的結果。最後，我們會利用指尖定位結果決定幾個不受手勢旋轉影響的特徵，並做實驗統計各手勢特徵的分佈情形，在決定手勢特徵後即可用來辨識手勢。由實驗結果顯示本系統辨識率為93.5%，且處理速度為每秒22張影像，能準確與即時的辨識手勢。

Nowadays, HCI(Human Computer Interaction) is an important part of technological development. A good HCI can often increase user’s attention and acceptance. Besides, using hand gesture to control device is currently one of a trend of HCI development, because hand gesture is an intuitive and simple way to communicate with others. Therefore, the purpose of this thesis is to develop a hand gesture recognition system for numbers (0-9) to be a human computer interaction way.
In hand gesture extraction phase, instead of using skin color detection like many other researches, we combine moving object detection and skin detection to extract hand gesture. The advantage of this method is that it can remove most of the noise with complex background. Then fingertip positioning is applied as first step of hand gesture recognition. The algorithm of fingertip positioning uses particles to diffuse to the contour of hand randomly. After the diffusion, particle selection and particle grouping are used to distinguish different fingertips, and the fingertip positions are the average position of each group’s particles. Based on the fingertip positioning result, we have carried out some experiments to decide features which are not affected by hand gesture rotation, and the features are used to recognize hand gestures. From the experimental results, it shows that the proposed method can operate in real-time at a frame rate of 22fps with good recognition rate.

[1] H. Lilha and D. Shivmurthy, “Analysis of pixel level features in recognition of real life dual-handed sign language data set,” International Conference on Recent Trends in Information Systems, pp. 246-251, Dec. 2011.
[2] M. Elmezain, A. Al-Hamadi, J. Appenrodt and B. Michaelis, “A hidden Markov model-based continuous gesture recognition system for hand motion trajectory,” International Conference on Pattern Recognition, pp. 1-4, Dec. 2008.
[3] S. Zhao, L. Shen and W. Tan, “A method of dynamic hand gesture detection based on local background updates and skin color model,” International Conference on Computer Application and System Modeling, vol. 5, pp. V5-657-V5-660, Oct. 2010.
[4] M. Geetha, R. Menon, S. Jayan, R. James and G.V.V. Janardhan, “Gesture recognition for American Sign Language with polygon approximation,” IEEE International Conference on Technology for Education, pp. 241-245, Jul. 2011.
[5] 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, Nov. 2011.
[6] X. Yin and X. Zhu, “Hand posture recognition in gesture-based human-robot interaction,” IEEE Conference on Industrial Electronics and Applications, pp. 1-6, May 2006.
[7] E.-J. Holden and R. Owens, “Recognising moving hand shapes,” Proceedings of International Conference on Image Analysis and Processing, pp. 14-19, Sep. 2003.
[8] H. Patel and M. P. Wankhade, “Human tracking in video surveillance,” International Journal of Emerging Technology and Advanced Engineering, vol. 1, no. 2, pp. 1-5, Dec. 2011.
[9] J. Heikkila and O. Silven, “A real-time system for monitoring of cyclists and pedestrians,” Second IEEE Workshop on Visual Surveillance, pp. 74-81, Jul. 1999.
[10] M. Soriano, B. Martinkauppi, S. Huovinen and M. Laaksonen, “Using the skin locus to cope with changing illumination conditions in color-based face tracking,” Proceedings of IEEE Nordic Signal Processing Symposium, pp. 383-386, Jul. 2000.
[11] Y. Wang and B. Yuan, “A novel approach for human face detection from color images under complex background,” Pattern Recognition, vol. 34, pp. 1983-1992, Oct. 2001.
[12] D. Chai and A. Bouzerdoum, “A bayesian approach to skin color classification in YCbCr color space,” Proceedings of IEEE Region Ten Conference, vol. 2, pp. 421-424 , Sep. 2000.
[13] 井上誠喜, 八木伸行, 林正樹, 中須英輔, 三谷公二, 奧井誠人 著, 吳上立, 林宏墩 譯, C語言數位影像處理, 台北市, 全華科技圖書股份有限公司, 民國九十五年。
[14] L. He, Y. Chao and K. Suzuki, “A run-based two-scan labeling algorithm,” IEEE Transactions on Image Processing, vol. 17, no. 5, pp. 749-756, May 2008.
[15] L. He, Y. Chao, K. Suzuki and K. Wu, “Fast connected-component labeling,” Pattern Recognition, vol. 42, no. 9, pp. 1977-1987, Sep. 2009.
[16] K.-J. Hsiao, T.-W. Chen and S.-Y. Chien, “Fast fingertip positioning by combining particle filtering with particle random diffusion,” IEEE International Conference on Multimedia and Expo, pp. 977-980, Apr.-Jun. 2008.
[17] L.-K. Lee, S.-Y. An and S.-Y. Oh, “Robust fingertip extraction with improved skin color segmentation for finger gesture recognition in human-robot interaction,” IEEE Congress on Evolutionary Computation, pp. 1-7, Jun. 2012.
[18] 岡薩雷斯 著, 繆紹綱 譯, 數位影像處理, 台北市, 台灣培生教育出版股份有限公司, 民國九十八年。