Weighted Median Filters for Multichannel Signals

Weighted medians over multichannel signals are not uniquely defined. Due to its simplicity, Astola 's Vector Median (VM) has received considerable attention particularly in image processing applications. In this paper, we show that the VM and its direct extension the Weighted VM are limited as...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on signal processing Vol. 54; no. 11; pp. 4271 - 4281
Main Authors Yinbo Li, Arce, G.R., Bacca, J.
Format Journal Article
LanguageEnglish
Published New York, NY IEEE 01.11.2006
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Applied sciences
Array signal processing
Arrays
Collaborative work
Color
Computational complexity
Derivation
Detection, estimation, filtering, equalization, prediction
Exact sciences and technology
Filtering
Filters
Image processing
Information, signal and communications theory
Mathematical analysis
Miscellaneous
Multichannel
Multichannel signal processing
Multidimensional signal processing
Multidimensional systems
nonlinear filtering
Signal and communications theory
Signal processing
Signal, noise
Telecommunications and information theory
vector medians
Virtual manufacturing
weighted medians
Weighting filter
Array signal processing
Optimal filter
Image processing
Multichannel signal processing
vector medians
Independent component analysis
weighted medians
Color image
Non linear filtering
Multichannel filter
Simulation
Cross correlation
Signal processing
Maximum likelihood
nonlinear filtering
Localization
Multiple channel
Median filter
Image denoising
Online AccessGet full text

Cover

More Information
Summary:Weighted medians over multichannel signals are not uniquely defined. Due to its simplicity, Astola 's Vector Median (VM) has received considerable attention particularly in image processing applications. In this paper, we show that the VM and its direct extension the Weighted VM are limited as they do not fully utilize the cross-channel correlation. In fact, VM treats all sub-channel components independent of each other. By revisiting the principles of Maximum Likelihood estimation of location in a multivariate signal space, we propose two new and conceptually simple multichannel weighted median filters which can capture cross-channel information effectively. Their optimal filter derivations are also presented, followed by a series of simulations from color image denoising to array signal processing where the advantages of the new filtering structures are illustrated
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1053-587X
1941-0476
DOI:10.1109/TSP.2006.881208