研究生: |
李世淵 |
---|---|
論文名稱: |
手勢辨識中非標的手勢模型之研究 Anti-Gesture Model For Gesture Recognition |
指導教授: | 楊熙年 |
口試委員: | |
學位類別: |
碩士 Master |
系所名稱: |
電機資訊學院 - 資訊系統與應用研究所 Institute of Information Systems and Applications |
論文出版年: | 2005 |
畢業學年度: | 93 |
語文別: | 中文 |
論文頁數: | 62 |
中文關鍵詞: | 隱藏式馬可夫模型 、似然度值 、門檻值 、手勢分割 |
相關次數: | 點閱:59 下載:0 |
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 |
在手勢辨識的系統中,一個重要的問題是如何有效地將非手勢(non-gesture)給排除(reject),通常是利用隱藏式馬可夫模型來做手勢辨識,然而利用隱藏式馬可夫模型來作辨識時,其辨識結果是一個似然度值(Likelihood),這樣的值只是一個相對的值而非絕對,因此辨識的結果只能告訴我們系統中哪一個手勢和我們輸入的手勢訊號最像,而無法告訴我們輸入的手勢訊號是否為一有效的手勢,意即若輸入的手勢訊號為非手勢(non-gesture)時就會發生問題。前人利用隱藏式馬可夫模型來作手勢辨識通常會將手勢訊號進行分段(Segmentation)的前處理,也就是輸入的手勢訊號只能是之前定義的手勢,而不能包含或是為一個非手勢。有的系統也作了一些限制以避免輸入非手勢而導致錯誤,他們限制使用者在開始作某個手勢時先停頓幾秒,做完之後再停頓幾秒,這樣的系統在實用性上離真實的連續手勢辨識系統還有一段距離。
本論文提出的「非標的手勢模型(Anti-Gesture Model)」提供了一個機率上明確的門檻值(Threshold)以排除非手勢,經過實驗證實可以有效的將非手勢予以排除,並正確地辨識出示範者的手勢。本論文所提出的「非標的手勢模型」可以廣泛的應用在離散型態的隱藏式馬可夫模型和連續型態的隱藏式馬可夫模型。此方法簡易且運算的時間複雜度低。
此外,經過實驗證實,也可利用「非標的手勢模型」來做手勢分割(Gesture Segmentation)。此方法可從一段正確輸入的手勢及非手勢訊號中正確地偵測出手勢訊號的部分,因此,我們相信這將提升連續手勢辨識系統的實用性。
參考文獻(Bibliography):
[L. Rabiner ,1986] L. Rabiner and B. Juang. ,"An Introduction to Hidden Markov Models" , IEEE ASSP Magazine, pages 4–16, 1986.
[L. R. Rabiner,1989] L. R. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition”, IEEE Trans on ASSP, Vol.77, No.2, pp 257-286, Feb. 1989.
[Wilpon, J.G. ,1989] Wilpon, J.G., Lee,C.H., Rabiner,L .R., "Application of Hidden Markov Models for Recognition of a Limited Set of Words in Unconstrained Speech," ICASSP-89, vol.3,pp.254-257.
[Richard C. Rose ,1990] Richard C. Rose , Douglas B. Paul, "A Hidden Markov Model Based Keyword Recognition System," ICASSP-90, vol.1 pp.129-132.
[Wilpon, Jay G. ,1990] Wilpon, Jay G., Rabiner,L awrence R., Lee,Chin-Hui, Goldman,E .R., "Automatic Recognition of Keywords in Unconstrained Speech Using Hidden Markov Models," IEEE Trans. on ASSP, vol.38, No.11, pp.1870-1878, Nov. 1990.
[L.D. Wilcox ,1992] L.D. Wilcox and M.A. Bush, "Training and Search Algorithms for an Interactive Wordspotting System", Proc. Int'l Conf. Acoustics,Speech, and Signal Processing, vol. II, pp. 97-100, San Francisco,1992.
[Richard C. Rose ,1992] Richard C. Rose, "Discriminant Wordspotting Techniques for Rejection Non-Vocabulary Utterances in Unconstrained Speech", Proc. IEEE Int'l Conf. Acoustics, Speech, and Signal Processing, vol. II, pp. 105-108, San Francisco, 1992.
[Boite, J-M ,1993] Boite, J-M, Bourlard, H , D’hoore, B and Haesen, M, "A new approach towards keyword spotting", Proc. Of EuroSpeech, 1993,1273-1276.
[Bourlard, H. ,1994] Bourlard, H., D’hoore, B. & Boite, J.-M. ,"Optimizing recognition and rejection performance in word-spotting systems",IEEE Proc. ICASSP-94, v.1, 373-376.
[Rahim,M. G. ,1995] Rahim,M. G., Lee,C. H., Juang,B.H., "Robust Utterance Verification for Connected Digits Recognition", ICASSP-95, Vol.1, pp.285-288.
[J. Caminero ,1996] J. Caminero, C. de la Torre, L. Villarrubia, C. Mart□n and L. Hern□ndez,"On-line Garbage Modeling with Discriminant Analysis for Utterance Verification",4th International Conference on Spoken Language Processing, Philadelphia, PA, USA October 3-6, 1996.
[E. Lleida ,1996] E. Lleida and R. C. Rose, "Likelihood ratio decoding and confidence measures for continuos speech recognition'', in Proceedings of ICSLP'96, Philadelphia, October 1996, vol. I, pp. 478--481.
[J. Gloger ,1997] J. Gloger, A. Kaltenmaier, E.Mandler, and L. Andrews. ,"Reject Management in a Handwriting Recognition System", In Int. Conference on Document Analysis and Recognition (ICDAR),pages 556–559, Ulm, Germany, Aug. 1997.
Mazin G. Rahim ,1997] Mazin G. Rahim, Chin-Hui Lee and Biing-Hwang Juang, "Discriminative utterance verification for connected digits recognition,'' IEEE Trans. on Speech and Audio Proc., vol. 5, 1997, pp. 266-277.
[J. Dolfing ,1998] J. Dolfing and A. Wendemuth. ,"Combination of Confidence Measures in Isolated Word Recognition", In 5th Int. Conference on Spoken Language Processsing (ICSLP), pages 3237–3240, Sydney, Australia, Dec. 1998.
[D. Jouvet ,1999] D. Jouvet, K. Bartkova and G. Mercier, "Hypothesis Dependent Threshold Setting for Improved Out of Vocabulary Data Rejection", IEEE Proc. ICASSP-99.
[Hyeon-Kyu Lee ,1999] Hyeon-Kyu Lee and Jin H. Kim,"An HMM-Based Threshold Model Approach for Gesture Recognition",IEEE Transactions on Pattern Analysis And Machine Intelligence, Vol. 21, No. 10, October 1999.
[S. O. Kamppari ,2000] S. O. Kamppari and T. J. Hazen. ,"Word and phone level acoustic confidence scoring", In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Istanbul,Turkey, June 2000.
[T. Hazen ,2001] T. Hazen and I. Bazzi. ,"A Comparison and Combination of Methods for OOV Word Detection and Word Confidence Scoring", In IEEE Int. Conference on Acoustics, Speech,and Signal Processing (ICASSP), Salt Lake City, Utah, May 2001.
[鐘林 ,2002] 鐘林,“漢語語音辨別說話驗證”,北京清華大學碩士論文,民國91年
[S. Marukatat ,2002] S. Marukatat, T. Arti`eres, P. Gallinari,B. Dorizzi,"Rejection measures for Handwriting sentence Recognition",Frontiers in Handwriting Recognition, 2002. Proceedings. Eighth International Workshop on.
[Anja Brakensiek ,2003] Anja Brakensiek,Rottland Rottland,Gerhard Rigoll,"Confidence Measures for an Address Reading System ",Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003).
[Manuele Bicegoa ,2004] Manuele Bicegoa,Vittorio Murinoa, M□rio A.T. Figueiredob,"Similarity-based classification of sequences using hidden Markov models",Pattern Recognition, vol 37(12), pp. 2281-22