信号处理中基于最小二乘法的提升小波的构造  

Construction of compactly supported biorthogonal wavelet based on lifting scheme

作　　者：梁茜[1] 丁宣浩[1] 何郁波[2] 

机构地区：[1]桂林电子科技大学数学与计算科学学院,桂林541004 [2]怀化学院数学系,湖南怀化418008

出　　处：《计算机工程与应用》2008年第13期156-158,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of China under Grant No.10361003);广西省自然科学基金(the Natural Sci- ence Foundation of Guangxi Province of China under Grant No.0542046);广西研究生教育创新计划项目( Innovation Project Guangxi Graduate Education,No.2006105950701M03)

摘　　要：在信号处理的应用背景下研究提升小波的构造方法。在提升小波的构造过程中预测算子和更新算子的选取不能混为一谈,为了更准确地将信号分解成低频分量和高频分量,提出更新算子的选取标准是各分量的和等于1/2,利用最小二乘法选取预测算子,并将构造出的提升小波运用于信号消噪,进一步研究预测算子和更新算子的选取规律,得到了较好的实验效果,验证了结论的正确性和实用性。When construct the lifting wavelet,the methods choosing predicting operator and updating operator are different.In this paper,we make a new criteria how to choose the updating operator in order to decompose signal into low frequency components and high frequency components more accurately,which is that the sum of the updating operator＇s components is 1/2,and then we choose predicting operator according to the least square theory.Some examples of lifting wavelet are applied to signal de-noising. We search the law of choosing predicting and updating operator,and get a good de-noising result.It proves that this method is valid.

关 键 词：提升方案 更新算子 预测算子 最小二乘法 

分 类 号：TN911[电子电信—通信与信息系统]