Adaptive linear combination of weighted medians

Kang Sun Choi, Aldo W. Morales, Sung Jea Ko

Research output: Contribution to journalConference article

Abstract

In our previous literature1, we proposed a class of nonlinear filters whose output is given by a linear combination of weighted medians (LCWM) of the input sequence. We showed that, unlike the median type filters having the lowpass response, the LCWM filters consisting of weighted median subfilters can not only suppress both Gaussian noise and impulsive noise effectively, but also offer various frequency characteristics including lowpass, bandpass, and highpass responses. In an attempt to improve the performance of LCWM filters, we propose an adaptive LCWM (ALCWM) filter which consists of directional weighted median subfilters with different geometric structures. The weighting factor of each subfilter is adaptively determined using the similarity between the directional subwindow and the local geometric image features of interest. It is shown experimentally that the ALCWM filter performs better than the aforementioned filters including the median and the LCWM filters in preserving more details.

Original languageEnglish (US)
Pages (from-to)484-492
Number of pages9
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume4667
DOIs
StatePublished - Jan 1 2002

Fingerprint

Median filters
Median Filter
Linear Combination
filters
Gaussian noise (electronic)
Impulse noise
Filter
Adaptive filters
Impulsive Noise
Nonlinear Filters
Adaptive Filter
Gaussian Noise
Geometric Structure
Weighting
nonlinear filters
adaptive filters
random noise
Output
preserving
output

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

@article{1a90dc6bb31e41589964b5baea89cda9,
title = "Adaptive linear combination of weighted medians",
abstract = "In our previous literature1, we proposed a class of nonlinear filters whose output is given by a linear combination of weighted medians (LCWM) of the input sequence. We showed that, unlike the median type filters having the lowpass response, the LCWM filters consisting of weighted median subfilters can not only suppress both Gaussian noise and impulsive noise effectively, but also offer various frequency characteristics including lowpass, bandpass, and highpass responses. In an attempt to improve the performance of LCWM filters, we propose an adaptive LCWM (ALCWM) filter which consists of directional weighted median subfilters with different geometric structures. The weighting factor of each subfilter is adaptively determined using the similarity between the directional subwindow and the local geometric image features of interest. It is shown experimentally that the ALCWM filter performs better than the aforementioned filters including the median and the LCWM filters in preserving more details.",
author = "Choi, {Kang Sun} and Morales, {Aldo W.} and Ko, {Sung Jea}",
year = "2002",
month = "1",
day = "1",
doi = "10.1117/12.468011",
language = "English (US)",
volume = "4667",
pages = "484--492",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

Adaptive linear combination of weighted medians. / Choi, Kang Sun; Morales, Aldo W.; Ko, Sung Jea.

In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 4667, 01.01.2002, p. 484-492.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Adaptive linear combination of weighted medians

AU - Choi, Kang Sun

AU - Morales, Aldo W.

AU - Ko, Sung Jea

PY - 2002/1/1

Y1 - 2002/1/1

N2 - In our previous literature1, we proposed a class of nonlinear filters whose output is given by a linear combination of weighted medians (LCWM) of the input sequence. We showed that, unlike the median type filters having the lowpass response, the LCWM filters consisting of weighted median subfilters can not only suppress both Gaussian noise and impulsive noise effectively, but also offer various frequency characteristics including lowpass, bandpass, and highpass responses. In an attempt to improve the performance of LCWM filters, we propose an adaptive LCWM (ALCWM) filter which consists of directional weighted median subfilters with different geometric structures. The weighting factor of each subfilter is adaptively determined using the similarity between the directional subwindow and the local geometric image features of interest. It is shown experimentally that the ALCWM filter performs better than the aforementioned filters including the median and the LCWM filters in preserving more details.

AB - In our previous literature1, we proposed a class of nonlinear filters whose output is given by a linear combination of weighted medians (LCWM) of the input sequence. We showed that, unlike the median type filters having the lowpass response, the LCWM filters consisting of weighted median subfilters can not only suppress both Gaussian noise and impulsive noise effectively, but also offer various frequency characteristics including lowpass, bandpass, and highpass responses. In an attempt to improve the performance of LCWM filters, we propose an adaptive LCWM (ALCWM) filter which consists of directional weighted median subfilters with different geometric structures. The weighting factor of each subfilter is adaptively determined using the similarity between the directional subwindow and the local geometric image features of interest. It is shown experimentally that the ALCWM filter performs better than the aforementioned filters including the median and the LCWM filters in preserving more details.

UR - http://www.scopus.com/inward/record.url?scp=0036057276&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036057276&partnerID=8YFLogxK

U2 - 10.1117/12.468011

DO - 10.1117/12.468011

M3 - Conference article

VL - 4667

SP - 484

EP - 492

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -