結語

　　本文提出了一種采用7Hu不變矩特征量等多種圖像特征相融合的SVMs手語識別方法。實驗表明，在手語識別中，采用圖像全局和局部特征相結合的方法，可獲得較高的識別率，為手語識別方法的早日推廣應用提供了理論依據(jù)。

　　參考文獻：

　　[1] TRIESCH J, MALSBURG C.ROBUST. Classification of Hand Postures Against Complex Background[C]. In: Intl Conf on Automatic Face and Gesture Recognition, 1998

　　[2] PARALEL HIDDEN. Markov Models for American Sign Language Recognition[C].Proceedings of the International Conference on Computer Vision, Kerkyra, Greece, September 22-25,1999

　　[3] 高文, 陳熙霖, 馬繼勇, 王兆其. 基于多模式接口技術的聾人與正常人交流系統(tǒng)[J]. 計算機學報, 2000.1

　　[4] YANG QUAN and PENG JINYE. Application of Improved Sign Language Recognition and Synthesis Technology in IB[C]. 3rd IEEE Conference on Industrial Electronics and Applications, June 2008.

　　[5] JIANPING FAN, YULI GAO, HANGZAI LUO. Integrating Concept Ontology and Multitask Learning to Achieve More Effective Classifier Training for Multilevel Image Annotation [J]. IEEE Transactions on Image Processing, Vol.17, No.3, 2008

　　[6] 吳銳航, 李紹滋, 鄒豐美. 基于SIFT特征的圖像檢索[J].計算機應用研究, 第25卷第2期, 2008

　　[7] 中國聾人協(xié)會.中國手語[M]. 北京:北京華夏出版社, 1991

　　[8] ZHANG SHU-YA, ZHAO YI-MING, LI JUN-LI. Algorithm and Implementation of Image Classification based on SVM[J]. Computer Engineering and Applicationgs, 2007

　　[11] KONG RUI, ZHANG BING. A Fast Algorithm of SVM Based on Geometry[J]. Journal of Image and Graphics, Vol. 12, No. 6, June 2007

　　[12] W-Y. MA, B.S. MANJUNATH. Texture features and learning similarity[J]. IEEE CVPR, pp.425-430, 1996

　　[13] C. CARSON, S. BELONGIE, H. GREENSPAN, J. MALIK. Blobworld: Image segmentation using expectation-maximization and its application to image querying[J]. IEEE Trans. PAMI, 2002