研究生: |
韓承翰 Cheng-han Han |
---|---|
論文名稱: |
以降維SURF為基礎的手勢辨識 Reduced Dimensional SURF Based Hand Gesture Recognition |
指導教授: |
陳志明
Chih-ming Chen 許新添 Hsin-teng Hsu |
口試委員: |
劉昌煥
Chang-huan Liu 施慶隆 Ching-long Shih |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電機工程系 Department of Electrical Engineering |
論文出版年: | 2010 |
畢業學年度: | 98 |
語文別: | 中文 |
論文頁數: | 51 |
中文關鍵詞: | 手勢辨識 、加速強健特徵 、主量分析 |
外文關鍵詞: | hand gesture recognition, SURF, PCA |
相關次數: | 點閱:327 下載:2 |
分享至: |
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 |
近年來隨著個人電腦使用的普及,人們開始尋找除了鍵盤和滑鼠以外較為自然的方式作為與電腦溝通的介面,而手勢辨識就是目前熱門研究的主題,應用的範圍包括人機介面、遊戲、家電控制等。本論文以加速強健特徵(speeded-up robust features, SURF)為基礎,使用主量分析法(principal component analysis, PCA)對SURF特徵作降維,用於靜態手勢的辨識。SURF是在尺度空間(scale space)中尋找穩定點,計算其主要方向,用於匹配特徵點的對齊,而後在鄰近區域內的Haar小波響應當作紋理特徵進而對特徵點加以描述,因此可以克服手勢辨識中手勢影像的縮放大小、旋轉變化、光影變幻等干擾。經由PCA降維取出重要的特徵資訊進行匹配時的加速運算,最後辨識出六種手勢。根據實驗結果得知,使用降維SURF比SURF的手勢辨識正確率還高,在辨識時間上花的時間也少。
Gesture recognition is a popular research topic. The application includes human-computer interaction interface for video games and other household appliances etc. In this research, we use SURF(speeded-up robust features) based with PCA(principal component analysis) for static hand gesture recognition. First, we find the stable points in scale space. Moreover, we use a Hessian Matrix-based measure for the detector, because of its good performance in computation time and accuracy. Next, in order to be invariant to rotation, we detect the orientation of the points by means of Haar-wavelet. Besides, we also use this method for the extraction of the descriptor.
SURF is good features due to their distinctive, scale-invariant and rotation-invariant. It is also robust in illumination variation. Therefore, we use SURF-PCA for additional speed up in recognition. In the results, we have presented a good performance in increased accuracy and faster recognition.
[1] T. Iijima, "Basic theory of pattern normalization," Bulletin of the Electrotechnical Laboratory, pp. 368-388, 1962.
[2] A. P. Witkin, "Scale space filtering," Proceedings of the International Joint. Conference on Artificial Intelligence, pp. 1019-1021, 1983.
[3] J. J. Koenderink, "The structure of image," Biological Cybernetics, pp. 363-370, 1984.
[4] J. Sporring, "The entropy of scale-sapce," Proceedings of the 13th International Conference on Pattern Recognition, pp. 900-904, 1996.
[5] T. Lindeberg, Scale-space Theory in Computer Vision: Kluwer Academic Publisher, 1994.
[6] D. Marr and E. Hildreth, "Theory of edge detection," Proceedings of the Royal Society, pp. 187-217, 1980.
[7] H. P. Moravec, "Towards automatic visual obstacle avoidance," Proceedings of the 5th International Joint Conference on Artificial Intelligence, 1977.
[8] C. Harris and M. Stephens, "A combined corner and edge detector," Proceedings of the Fourth Alvey Vision Conference, pp. 147-152, 1988.
[9] K. Mikolajczyk and C. Schmid, "Indexing based on scale invariant interest points," International Conference on Computer Vision, pp. 525-531, 2001.
[10] D. G. Lowe, "Object recognition from local scale-invariant features," International Conference of Computer Vision, vol. 60, pp. 1150-1157, 1999.
[11] Y. Ke and R. Sukthankar, "PCA-SIFT: A more distinctive representation for local image descriptors," Proceedings Conference Computer Vision and Pattern Recognition, pp. 511-517, 2004.
[12] H. Bay, T. Tuytelaars, and L. Van Gool, "SURF: Speeded up robust features," Proceedings of European Conference on Computer Vision, pp. 404-417, 2006.
[13] D. G. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, vol. 60, pp. 91-110, 2004.
[14] P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol.2, pp. 1403-14102, 2003.
[15] L. Juan and O. Gwun, "A comparison of SIFT, PCA-SIFT and SURF," International Journal of Image Processing, vol.3, pp. 143-152, 2009.
[16] R. H. Liang and M, Ouhyoung, "A real-time continuous gesture recognition system for sign language," Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition, pp. 558-565, 1998.
[17] J. M. Rehg and T. Kanade, "DigitEyes: vision-based hand tracking for human-computer interaction," IEEE Workshop on Motion of Non-Rigid and Articulated Objects, pp. 16-22, 1994.
[18] 許宏昌, "主成份分析法於指尖亮點手勢辨識之應用," 國立中山大學海下技術研究所碩士論文, 2003.
[19] 曹文潔, "猜拳機," 國立中央大學電機工程研究所碩士論文, 2007.
[20] 李經寧, "即時手勢辨識系統應用於機上盒控制," 國立中央大學資訊工程研究所碩士論文, 2009.
[21] Y. Fang, J. Cheng, K. Wang and H. Lu, "Hand gesture recognition using fast multi-scale analysis," Proceedings of IEEE International Conference on Image and Graphics, 2007.
[22] B. Stenger, "Template based hand pose recognition using multiple cues," Proceedings of the 7th Asian Conference on Computer Vision: ACCV, 2006.
[23] C. L. Huang and S. H. Jeng, "A model-based hand gesture recognition system," Machine Vision and Application., vol. 12, pp. 243-258, 2001.