以数据手套为基础,分析了手形的几何关系,建立了虚拟手的模型,由数据手套的数据接口获取各指节的曲伸角度,建立手势标准样本库,并提出了基于BP神经网络的手势识别方法,用手势标准样本加以训练,使其具备识别手势的功能,并利用VC++编程实现BP神经网络,用Matlab验证实验结果的正确性.
This paper analyzes the geometric relation of hand shapes based on data glove. The model of virtual hand is constructed. The tortile angle data of each joints is got from the serial data port of the glove. The standard sample copy library is built. The paper gives a method of gesture recognition based on neuron networks and its test which uses. Put the BP Neuron Networks into practice with VC ++ to realize the gesture recognition, and validate the correcmess of the experiment, with MATLAB.