一种基于加速度传感器的虚拟手写数字特征提取及识别方法  

A Feature Extraction and Recognition Approach for Accelerometer Based Virtual Handwriting Digit

作　　者：薛洋[1] 金连文[1] 

机构地区：[1]华南理工大学电子与信息学院,广州510640

出　　处：《模式识别与人工智能》2011年第4期492-500,共9页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.U0735004);广东省自然科学基金项目(No.07118074)资助

摘　　要：本文提出了一种基于加速度传感器的虚拟手写数字特征提取及识别方法.该方法首先对书写时产生的三轴加速度信号投影,获得三个二维矢量.然后基于每个二维矢量提取反映加速度信号顺时针和逆时针旋转变化的特征点,并进行数字编码得到旋转特征码.接着采用归一化编辑距离来度量不同样本的旋转特征码间的差异,最后结合旋转特征和基于编辑距离的旋转特征码的距离测度,给出虚拟手写数字识别算法.与传统的时域原始特征、峰值谷值特征、FFT特征的识别性能对比实验表明本文方法的有效性.An approach for accelerometer based virtual digit feature extraction and recognition is proposed. Firstly, accelerations are projected on three planes respectively. Secondly, the rotation feature of the handwriting is extracted and coded. Then, normalized edit distance is used to measure the difference between different rotation feature codes. Finally, based on the rotation feature and edit distance, an algorithm of virtual handwriting digit recognition is given. Compared with time-domain feature, peak-valley feature and FFF feature, the proposed approach is effective.

关 键 词：旋转特征 三轴加速度信号 虚拟手写数字 编辑距离 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]