The rational filter for image smoothing

被引：47
作者：
Ramponi, G
机构：
[1] DEEI, University of Trieste, Trieste
来源：
IEEE SIGNAL PROCESSING LETTERS | 1996年 / 3卷 / 03期
关键词：
D O I：
10.1109/97.481156
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：
A nonlinear operator is presented that is able to effectively attenuate the noise that corrupts an image while introducing small distortions on the image details. It is described by a rational function, i.e., by the ratio of two polynomials in the input variables. Notwithstanding its simplicity, this operator proves to be more powerful than conventional methods for many noise distributions.
引用
收藏
页码：63 / 65
页数：3
相关论文
共 11 条
[1]   ALPHA-TRIMMED MEANS AND THEIR RELATIONSHIP TO MEDIAN FILTERS [J].
BEDNAR, JB ;
WATT, TL .
IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1984, 32 (01) :145-153
[2]   A QUANTITATIVE COMPARISON OF EDGE-PRESERVING SMOOTHING TECHNIQUES [J].
DUBUF, JMH ;
CAMPBELL, TG .
SIGNAL PROCESSING, 1990, 21 (04) :289-301
[3]  
GABBOUJ M, 1994, 1O TAMP U TECHN
[4]   A STRUCTURE FOR ADAPTIVE ORDER-STATISTICS FILTERING [J].
HIMAYAT, N ;
KASSAM, SA .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1994, 3 (03) :265-280
[5]   CENTER WEIGHTED MEDIAN FILTERS AND THEIR APPLICATIONS TO IMAGE-ENHANCEMENT [J].
KO, SJ ;
LEE, YH .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1991, 38 (09) :984-993
[6]   DIGITAL IMAGE SMOOTHING AND THE SIGMA FILTER [J].
LEE, JS .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1983, 24 (02) :255-269
[7]   DETECTION AND ESTIMATION USING AN ADAPTIVE RATIONAL-FUNCTION FILTER [J].
LEUNG, H ;
HAYKIN, S .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1994, 42 (12) :3366-3376
[8]  
RAMPONI G, 1995, P 2 IEEE INT C IM PR
[9]   ANALYSIS OF 2-DIMENSIONAL CENTER WEIGHTED MEDIAN FILTERS [J].
SUN, T ;
GABBOUJ, M ;
NEUVO, Y .
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING, 1995, 6 (02) :159-172
[10]   CENTER WEIGHTED MEDIAN FILTERS - SOME PROPERTIES AND THEIR APPLICATIONS IN IMAGE-PROCESSING [J].
SUN, T ;
GABBOUJ, M ;
NEUVO, Y .
SIGNAL PROCESSING, 1994, 35 (03) :213-229
12