异常点检测与Savitzky-Golay滤波算法在手写系统中的应用*

作者：朱墨子1，2,包鑫3 日期：2008-08-18/span> 浏览：4021 查看PDF文档

异常点检测与Savitzky-Golay滤波算法在手写系统中的应用*

朱墨子1，2,包鑫3
(1.中国科学院 合肥智能机械研究所，安徽 合肥 230031； 2.中国科学技术大学 信息科学技术学院，安徽 合肥 230027；
3.浙江大学 工业控制技术国家重点实验室，浙江 杭州 310027)

摘要：针对手写输入设备已成为一个新的研究热点，在自行研制的练字板程序和F-Tablet手写板的基础上，提出了一种基于3σ准则异常点检测与Savitzky-Golay滤波的预处理算法。首先利用3σ准则对力信息数据进行了异常点检测和剔除，然后对没有异常点的坐标数据进行了滤波,以减少噪声。实验结果表明，采用提出的预处理方法，可以消除大部分噪声和异常点的干扰，同时避免了如小波变换等方法的复杂计算，取得了令人满意的结果。
关键词：3σ准则；Savitzky-Golay滤波;标准正态变换;力信息
中图分类号：TP391.41文献标识码：A文章编号：1001-4551(2008)08-0005-03

Application of outlier detection and savitzky-golay filter in handwritten systems
ZHU Mo-zi1,2, BAO Xin3
(1.Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031, China;
2.School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China;
3.State Key Lab of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China)
Abstract: Aiming at the new research focus of handwriting infut devices, a preprocessing method based on outlier detection by 3σ rule and Savitzky-Golay filter was proposed and applied in F-Tablet and handwritten programs. Firstly, 3σ rule was used to detect outliers and remove it from the force information data, then Savitzky-Golay filter was used to reduce noise. The results show the effectiveness of proposed method. Using the method, most noises and outliers can be removed, and complex computation can be avoided.
Key words: 3σ rule； Savitzky-Golay filter; standard normal variate; force information