基于几何特征的手势识别方法  

Gesture recognition method based on geometric characteristics

作　　者：林水强 吴亚东[1] 陈永辉[1] 

机构地区：[1]西南科技大学计算机科学与技术学院,四川绵阳621010

出　　处：《计算机工程与设计》2014年第2期636-640,共5页Computer Engineering and Design

基　　金：国防基础研究基金项目(B3120110005;10ZG6102);四川省科技厅基金项目(2011JQ0041;11ZS2009);四川省教育厅重点基金项目(11ZA130;13ZA0169);绵阳市网络融合基金项目(12zxwk05)

摘　　要：研究基于手势图像几何特征的方法实现自然手势识别交互。基于肤色模型,提出一种多序列背景模型并结合肤色块跟踪和几何形状估计提取手势图像,通过分析手势几何特征计算特征参数,采用决策树分类方法对手势几何特征属性进行归纳判定,识别手势。实验结果表明,在常规背景并且室内光照良好的环境下,该方法对预定义的6种自然手势类型识别准确率达到94%以上,能够很好地完成实时多媒体交互应用。To achieve natural gesture recognition interaction, a method based on gesture geometric characteristics is studied. Based on skin-color model, a kind of multi-sequences background model is proposed, combining skin-color block tracking and geometric shape esti- mating to extract gesture images. To compute gesture parameters, gesture geometric characteristics are analyzed. To distinguish and rec- ognize different hand gestures, decision tree classification method is adopted. Experimental results demonstrate that the recognition accu racy rate of the predefined six kinds of natural gesture types reaches 94% under the general background and indoor daytime well-lit envi- ronment. The gesture recognition system can implemen＇, the synchronized multimedia interactive applications effectively.

关 键 词：人机交互 手势识别 几何特征 多序列背景模型 决策树 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]