摘要
提出一种新型的手部姿态识别系统,用于控制多自由度假手.系统利用FSR传感器检测前臂肌肉的收缩情况来实现不同动作的识别.通过安装在手臂筒当中的FSR传感器获取不同手部姿态对应的信号大小,经过支持向量机SVM(support vector machine)分类器在2类数据之间布置一个超平面,并使数据距离此超平面距离最大而对2类数据进行线性的分隔,处理后归入相应手部运动模式.实验结果表明,该方法在一定程度上克服肌电信号缺点,并实现多达33种手部姿态识别.
In this article a new recognition system for hand gesture developed for the purpose of controlling active hand prosthesis is presented. The recognition system allows for the measurement and classification of muscle contraction around the lower arm. The singles obtained by the FSR sensors would be analyzed by the SVM divider, which is developed based on the theory of setting maximal distance between different categories, and then assigned to certain category. The experiment indicate that it can overcome the disadvantages of EMG signals to some extend and recognize thirty - three different hand gestures
出处
《机械与电子》
2009年第1期43-46,共4页
Machinery & Electronics
基金
国家自然科学基金重点资助项目(50435040
60675045)
长江学者和创新团队发展资助计划
关键词
FSR传感器
数据采集
动作识别
支持向量机
FSR sensor
data acquisition
gesture recognition
support vector machine