Optimality of the myriad filter in practical impulsive-noise environments

被引：91

作者：

Gonzalez, JG ^{[1
]}

Arce, GR

机构：

[1] Univ Delaware, Dept Elect & Comp Engn, Newark, DE 19716 USA

[2] Intellectual Property Syst, LLC, Wilmington, DE 19713 USA

来源：

IEEE TRANSACTIONS ON SIGNAL PROCESSING | 2001年 / 49卷 / 02期

基金：

美国国家科学基金会;

关键词：

alpha-stable distributions; Cauchy distribution; heavy tails; impulsive processes; median filters; Myriad filters; robust signal processing;

D O I：

10.1109/78.902126

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Linear filtering theory has been largely motivated by the characteristics of Gaussian signals, In the same manner, the proposed myriad filtering methods are motivated by the need for a flexible filter class with high statistical efficiency in non-Gaussian impulsive environments that can appear in practice. We introduce several important properties of the myriad filter and prove its optimality in the family of alpha -stable distributions.

引用

页码：438 / 441

页数：4

共 12 条

[1]

AMBIKE S, 1995, P INT WORKSH NONL SI

[2]

Arce G, 1997, THESIS U DELAWARE NE

[3]

ARCE GR, 1996, P AS C MONT CA NOV

[4]

Durrett R, 1996, PROBABILITY THEORY E

[5]

GONZALEZ JG, 1996, P C INF SCI SYST PRI

[6]

GONZALEZ JG, 1997, P IEEE ICASSP MUN GE

[7]

GONZALEZ JG, 1996, P IEEE ICASSP ATL GE

[8]

Hampel F. R., 1986, ROBUST STAT APPROACH

[9] Adaptive weighted myriad filter algorithms for robust signal processing in α-stable noise environments [J].

Kalluri, S ;

Arce, GR .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1998, 46 (02) :322-334

[10]

Nikias CL., 1995, SIGNAL PROCESSING AL

← 1 2 →