在本篇論文中，主要是研究人機互動的一個領域。而其中包含了肢體互動的方式，手語辨識系統則是其中的應用。在手語系統中，包含單字手語的辨識和連續手語的辨識。其中單字手語辨識的發展已經經過了很長的一段時間，所使用的方式是利用HMM或是DTW等方式來達到辨識的效果。而連續手語則是一個比較複雜的問題，其中連續手語序列的分割是最為難以解決的部分，所以本篇論文我們將專注於連續手語序列的分割。
在我們的連續手語系統當中，我們主要是使用PHMM來去做辨識，而主要的連續手語序列則是使用CRF模型來做分割。在連續手語當中，在兩個單字手語的區間會有一段轉換的過程，我們稱之為ME，或是非手語部分。CRF模型主要是利用我們所建立的手語單字模型，來去辨識我們沒有建立的非手語(ME)部分。在其中我們有訓練到的手語，其CRF模型的機率值會偏高。反之在我們沒訓練到的ME部分，CRF的機率值會偏低。因此我們藉由此特性可以成功的分割出手語部分和非手語(ME)的部分。
在我們的實驗環境中，我們使用了40個手語字彙與5個測試者。其中3個測試者來去做訓練，2個測試者做測試。每個測試者比劃出相同的5段手語做計算。我們計算出來的精確度和回復率分別是最佳92.5和88.5。結果說明了我們的手語辨識系統中有不錯的分割效能。

[1] Fang, G.; Gao, W.; Zhao, D.; “Large-Vocabulary Continuous Sign Language Recognition Based on Transition-Movement Models”, IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans, pp.1-9, Dec. 2006
[2] Gao, W; Fang, G; Zhao, D; and Yiqiang C, “Transition Movement Models for Large Vocabulary Continuous Sign Language Recognition,” Proc. Sixth IEEE Int’l Conf. Automatic Face and Gesture Recognition, pp. 553-558, May 2004.
[3] J, Ye; H, Yao; and F, Jiang; “Based on HMM and SVM Multilayer Architecture Classifier for Chinese Sign Language Recognition with Large Vocabulary,” Proc. Third Int’l Conf. Image and Graphics (ICIG ’04), pp. 377- 380, Dec. 2004
[4] Maebatake, M.; Suzuki, I.; Nishida, M.; Horiuchi, Y.; Kuroiwa, S,” Sign Language Recognition Based on Position and Movement Using Multi-Stream HMM," Second International Symposium. Universal Communication (ISUC ’08), pp.478-481, Dec. 2008
[5] Matsuo, T. ; Shirai, Y. ; Shimada, N. ; “Automatic Generation of HMM Topology for Sign Language Recognition,” 19th International Conference. Pattern Recognition (ICPR ’08), pp.1-4, 2009
[6] C. L.Wang,W. Gao, and S. G. Shan, “An approach based on phonemes to large vocabulary Chinese sign language recognition,” in Proc. IEEE Int. Conf. Autom. Face Gesture Recognit., 2002, pp. 411–416.
[7] B. Bauer and H. Hienz, “Relevant features for video-based continuous sign language recognition,” in Proc. 4th Int. Conf. Autom. Face Gesture Recognit., 2000, pp. 440–445.
[8] Mahmoud Elmezain, Ayoub Al-Hamadi, J¨org Appenrodt, Bernd Michaelis,“A Hidden Markov Model-Based Continuous Gesture Recognition System for Hand Motion Trajectory,” 19th International Conference. Pattern Recognition (ICPR '08), pp. 1-4, 2009
[9] Daniel Kelly, John Mc Donald, Charles Markham, "Continuous Recognition of Motion Based Gestures in Sign Language," IEEE 12th International Conference.Computer Vision Workshops (ICCV 2009), pp. 1073-1080, 2010
[10] J. Lafferty, A. McCallum, and F. Pereira, “Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data,” Proc. 18th Int’l Conf. Machine Learning, pp. 282-289, June 2001.
[11] H.M. Wallach, “Conditional Random Fields: An Introduction,”Technical Report MS-CIS-04-21, Univ. of Pennsylvania, 2004.