基于确定学习的数字手势识别  

Digital-hand Gesture Recognition Using Deterministic Learning

作　　者：刘凤琳[1] 林雯静 王清辉[1] 王颖[1] 温发林[1] LIU Fenglin;LIN Wenjing;WANG Qinghui;WANG Ying;WEN Falin(Longyan University,Longyan,Fujian 364000,China)

机构地区：[1]龙岩学院

出　　处：《龙岩学院学报》2019年第5期42-49,共8页Journal of Longyan University

基　　金：福建省中青年教师教育科研项目(JAT170558);福建省大学生创新创业训练计划项目(201811312032)

摘　　要：基于确定学习理论研究手势识别方法,并以阿拉伯数字0~9为例,通过2折和10折的交叉验证实验,阿拉伯数字0~9的识别率分别为95.83%和97.25%,即证明该方法具有高识别率。This paper is to develop a new method for hand gesture recognition based on deterministic learning theory and represented by Arabic numbers 0~9.By using the 2-fold and 10-fold cross-validation styles,the correct recognition rates of Arabic numbers 0~9 are reported to be 95.83%and 97.25%,respectively,which means the method for hand gesture recognition based on deterministic learning theory has a high recognition rate.

关 键 词：手势识别 确定学习 微软Kinect 手势动力学 RBF神经网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]