在這篇論文中，我們提出了一種新穎的方法，那就是使用在二值化圖片上尺度不變特徵轉換(SIFT)，我們是第一位提出這種使用尺度不變特徵轉換的方法，並且也證明這方法使用在手勢辨識是可行的，同時這種方法也能取代傳統的模板(template)方法，在使用模板方法中有許多限制，如演算複雜度會隨著旋轉角度和大小而成長，而在我們的方法中，旋轉、大小及光照都是可變的且同時也是即時運作的手勢辨識系統，然後在我們的方法中，只需要使用視訊球及低功率消耗的機器。在我們系統的學習階段中，我們首先利用SIFT演算法對二值化的圖片擷取特徵點，然後再利用已經跑好的K-means分群模型把這些不固定數量的特徵點轉換成固定長度大小的長方圖，再利用SVM去對這些長方圖做學習。

We present a novel way to use the Scale Invariance Feature Transform (SIFT) on binary images. As far as we know, we proposed employ SIFT on binary images for hand gesture recognition and provide more accurate result comparing to traditional template approaches. There exist many restrictions on template matching approaches, such as the rotation must be less than 15°, and the variation on scale, etc. However, our proposed approach is robust against rotations, scaling, illumination conditions, and can recognize hand gestures in real-time with only off-the-shelf camera such as webcams. The proposed approach employs the SIFT features on binary image, the k-means clustering to map keypoints into a unified dimensional histogram vector (bag-of-words), and the Support Vector Machine (SVM) to classify different hand gestures.

[1] N. H. Dardas and N. D. Georganas, “Real-Time Hand Gesture Detection and Recognition Using Bag-of-Features and Support Vector Machine Techniques,” IEEE Transaction On Instrumentation And Measurement, pp. 3592 – 3607, Nov. 2011.
[2] M. Panwar, “Hand gesture recognition based on shape parameters,” Computing, Communication and Applications (ICCCA), 2012 International Conference on, pp. 1–6, Feb. 2012.
[3] B. Stenger, “Template based hand pose recognition using multiple cues,” Proceedings of 7th Asian Conference on Computer Vision, pp. 551–560, 2006.
[4] G. Tofighi, S. A. Monadjemi, and N. Ghasem-Aghaee, “Rapid Hand Posture Recognition Using Adaptive Histogram Template of Skin and Hand Edge Contour,” Machine Vision and Image Processing (MVIP), 2010 6th Iranian, pp. 1–5, Oct. 2010.
[5] T. Kanungo, D. M. Mount, N. Netanyahu, C. Piatko, R. Silverman, and A. Y. Wu, “An efficient k-means clustering algorithm: Analysis and implementation,” IEEE Trans. Pattern Analysis and Machine Intelligence, pp. 881-892, 2002.
[6] H. Takimoto, S. Yoshimori, Y. Mitsukura, M. Fukumi, “Classification of hand postures based on 3D vision model for human-robot interaction,” IEEE International Symposium on Robot and Human Interactive Communication, pp. 292-297, Sept. 2010.
[7] W. Shuangqing, Z. Yin, Z. Sanyuan, Y. Xiuzi, C. Yiyu, Z. Jianmin, G. Soumita and C. Wenyu, Z. Jane, “2D motion detection bounded hand 3D trajectory tracking and gesture recognition under complex background,” Proceedings of the 9th Association for Computing Machinery's Special Interest Group on Computer Graphics and Interactive Techniques Conference on Virtual-Reality Continuum and its Applications in Industry, pp. 311-318, 2010
[8] M. Van den Bergh, L. Van Gool, ”Combining RGB and ToF Cameras for Real-time 3D Hand Gesture Interaction,” Workshop on Applications of Computer Vision (WACV), 2011 IEEE Workshop on, pp. 66-72, Jan. 2011.
[9] R. Fukui, M. Watanabe, M. Shimosaka, T. Sato, “Hand shape classification with a wrist contour sensor: development of a prototype device,” Proceedings of the 13th international conference on Ubiquitous computing, pp. 311-314, 2011.
[10] Z. Xu, C. Xiang, W. Wen-hui, Y. Ji-hai, L. Vuokko, W. Kong-qiao, “Hand gesture recognition and virtual game control based on 3D accelerometer and EMG sensors,” Proceedings of the 14th international conference on Intelligent user interfaces, pp. 401-406, 2009.
[11] J. Weston and C. Watkins, “Support vector machines for multi-class pattern recognition,” Proceedings of European Symposium on Artificial Neural Networks Bruges (Belgium), pp. 219-224, April 1999.
[12] C.-C. Chang and C.-J. Lin, LIBSVM: A Library for Support Vector Machines, 2001. [Online]. Available: http://www.csie.ntu.edu.tw/~cjlin/libsvm
[13] C.-W. Hsu and C.-J. Lin, “A comparison of methods for multi-class support vector machines,” IEEE Transactions on Neural Networks, pp. 415–425, Mar. 2002.
[14] J. H. Friedman, “Another approach to polychotomous classification,” Department of Statistics and Stanford Linear Accelerator Center Stanford University, 1997.
[15] P. Viola and M. Jones, “Robust real-time object detection,” International Journal of Computer Vision , pp. 137–154, 2004.
[16] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, pp. 91–110, Nov. 2004.
[17] S. Lazebnik, C. Schmid, and J. Ponce, “Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories,” Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2169-2178, 2006.
[18] Y. Jiang, C. Ngo, and J. Yang, “Towards optimal bag-of-features for object categorization and semantic video retrieval,” Proceedings of the ACM International Conference on Image and Video, pp. 494–501, 2007.
[19] L. Bretzner, I. Laptev, and T. Lindeberg, “Hand gesture recognition using multi-scale color features, hierarchical models and particle filtering,” Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition, pp. 405–410, 2002.
[20] S. McKenna and K. Morrison, “A comparison of skin history and trajectory-based representation schemes for the recognition of user specific gestures,” Pattern Recognition, pp. 999–1009, May 2004.
[21] K. Imagawa, H. Matsuo, R. Taniguchi, D. Arita, S. Lu, and S. Igi, “Recognition of local features for camera-based sign language recognition system,” in Proceedings of International Conference on Pattern Recognition, pp. 849–853, 2000.
[22] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, pages. 91-110, 2004.
[23] Scale-invariant feature transform, http://en.wikipedia.org/wiki/Scale-invariant_feature_transform, referenced on May 1st, 2012.