手語主要以手型、位置、動作、及手勢方向等因素組成。本論文運用影像處理技術擷取出雙手手掌，並使用費雪鑑別分析法辨識出手形與位置等資訊，作為一組狀態。而每當狀態更新，則立即做手語語意之辨識，並考慮新狀態的加入是否影響手語之連貫性。使用Kalman filter做雙手位置之追蹤，使雙手交錯時，系統仍然能分辨出左右手。辨識時也使用了KNN分類法，避免A手勢某樣本，與B手勢某樣本過於相似而造成的誤判。
本系統可達每秒辨識出8次以上雙手之手勢，角度誤差在15°~ -15°內，辨識率為96%，已具備基本連續手語辨識能力。但語意辨識為即時的，因此沒考慮如曲線移動等複雜手勢。

The sign language is composed of hand gesture，position movement and direction. This study uses image processing to extract human being palm ,and uses Fisher Linear Discriminant method to recognize hand gesture, and saves a new state when hand gesture change. Real-time recognition of the sign language is performed using the changing hand state. Using Kalman filter to track the evocations of both hands, the system can distinguish between left and right hands, when both hands are interlaced. The system also uses KNN search method to determine the best gesture, avoiding A gesture sample which is similar to B gesture sample, causing incorrect gesture results.
The system can recognize hands gesture eight times per second, the recognition rate is 96% with angle changes from 15° ~ -15°. So the system can continuously recognize the sign language. But the system is timely, so not considering the complexity of moving gesture.

[1] P. N. Belhumeur, J, P. Hespanha, D. J. Kriegman “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection” IEEE Transactions on pattern analysis and machine intelligence, vol.19, NO.7, pp. 711-720, July 1997.
[2] Lawrence R. Rabiner, A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings 1989.
[3] A. Albiol, L. Torres, and E.J. Delp, “Optimum Color Spaces for Skin Detection,” Image Processing, 2001. Proceedings. 2001 International Conference on, IEEE, Thessaloniki Greece, Vol. 1, pp. 122-124, Oct. 2001.
[4] C. Garcia and G. Tziritas, "Face detection using quantized skin color regions merging and wavelet packet analysis " Multimedia, IEEE Transactions on , Volume: 1 Issue: 3 , Sep 1999, Page(s): 264 -277.
[5] M.Soriano，S.Huovinen， B.Martinkauppi and M.Laaksonen，”Using the Skin Locus Cope with Changing Illumiation Condition in Color-Based Face Tracking”Proceedings of IEEE Nordic Signal Processing Symposium，pp.383-386 2000
[6] T.Morris and V.Chauhan，”Facial feature tracking for cursor control “ Journal of Network and Computer Application，Vol 29 No.1 pp62-80 2006 正規劃
[7] R.L. Hsu,”Face detection in color images，”IEEE Transaction on Pattern Analysis and Machine Intelligence， Vol.24，pp. 696-706，2002
[8] Rudolf Emil Kalman，” A New Approach to Linear Filtering and Prediction Problems” Columbia university，1960
[9] Jhih-Cheng Hian，“Tracking of sign trajectories associated with hand- hand occlusion “，National Cheng Kung University，Computer Science and Information Engineering，Dec 2008
[10] 蔡仲齡，” 含語者驗證之小型場所人臉辨識門禁系統的研發”， 國立成功大學工程科學所碩士論文 2008
[11] 王建中，”鑑別性隱藏式馬可夫模型應用於人臉辨識” ，國立成功大學 資訊工程系碩士論文，2005
[12] 張書龍，”具辭書式情境感知之語音導引機器人” 成功大學工程科學系碩士論文， 2009
[13] 江明晏，” 耦合隱藏式馬可夫模型於雙手手勢辨識” 成功大學資訊工程學系碩士論文， 2007
[14] 洪兆欣，”以軌跡辨識為基礎之手勢辨識系統”中央大學資訊工程所碩士論文，2006
[15] 簡志城，” 手勢涉及雙手遮蔽的軌跡追蹤”， 國立成功大學資訊工程所碩士論文， 2008
[16] 石柏良， “利用灰關聯分析法建立即時手部動作辨識系統”，成工大學醫學工程研究所碩博士班 ，2008
[17] 葉政憲，”手部資訊擷取系統之設計與應用”， 國立成功大學電機工程所碩士論文， 2005
[18] 沈全發，” 機械式手套與虛擬實境之整合研究”， 國立成功大學電機工程所碩士論文， 2002
[19] 胡冠宇，”基於膚色之裸體影像偵測之研究”國立成功大學工程科學系碩士論文， 2004
[20] 張唐祐，”改良式投影演算法於車牌辨認之應用”， 國立成功大學電腦與通訊工程所碩士論文， 2008
[21] 中華民國聾人協會，手能生橋、第一冊
[22] Rafael C. Gonzalez, Richard E. Woods原著，繆紹綱譯，數位影像處理，普林斯頓國際