智能系统学报2018，Vol.13Issue(4)：619-624,6.DOI:10.11992/tis.201708003
对偶树复小波与空域信息的手势识别分类研究
Research on gesture recognition and classification of dual-tree complex wavelet and spatial information
摘要
Abstract
To improve the validity of features obtained in gesture recognition,in this paper,we propose a fusion feature that combines spatial and dual-tree complex wavelet transform features.These features mainly include seven compon-ents(horizontal position,vertical position,aspect ratio,rectangular degree,Hu moments,etc.)and 27 dimensional fea-tures,comprising 11 dimensional spatial features and 16 dimensional dual-tree complex wavelet transform features.We employ the optimal distance support vector machine(BD-SVM)classification method to optimize training samples for the classifier optimization algorithm.The experimental results show that,in a test of gestures "1～9" using the RBF ker-nel function,the highest average recognition accuracy is 90.33％and the average recognition time is 0.026 s.These res-ults reveal that the proposed method demonstrates excellent static gesture recognition,a high training speed,and accur-acy in identification.关键词
手势识别/空域特征/对偶树复小波/特征融合/分类器优化/BD-SVM/径向基核函数/静态测试Key words
gesture recognition/spatial feature/dual-tree complex wavelet/feature fusion/classifier optimization/BD-SVM/radial basis kernel function/static test分类
信息技术与安全科学引用本文复制引用
贾鹤鸣,朱传旭,张森,杨泽文,何东旭..对偶树复小波与空域信息的手势识别分类研究[J].智能系统学报,2018,13(4):619-624,6.基金项目
中央高校基本科研业务费专项资金项目(2572014BB03) （2572014BB03）
国家自然科学基金项目 (31470714,51609048) （31470714,51609048）
黑龙江省研究生教育创新工程项目(JGXM_HLJ_2016014). （JGXM_HLJ_2016014）
