The effect of median filtering on edge location estimation

G. J. Yang, T. S. Huang

Research output: Contribution to journalArticle

Abstract

We study the effect of noise reduction preprocessing, specifically median filtering and averaging, on the accuracy of edge location estimation using least squares. The original edge is either a step or a linear ramp, corrupted by white Gaussian noise or binary symmetrical channel noise. The surprising conclusion is that in the case of white Gaussian noise, neither median filtering nor averaging improves the estimation accuracy. In the case of binary symmetrical channel noise, median filtering does improve the estimation accuracy for ramp edges, which are reasonable models for real-life edges.

Original languageEnglish (US)
Pages (from-to)224-245
Number of pages22
JournalComputer Graphics and Image Processing
Volume15
Issue number3
DOIs
StatePublished - Mar 1981
Externally publishedYes

Fingerprint

effect
noise reduction

ASJC Scopus subject areas

  • Environmental Science(all)
  • Earth and Planetary Sciences(all)

Cite this

The effect of median filtering on edge location estimation. / Yang, G. J.; Huang, T. S.

In: Computer Graphics and Image Processing, Vol. 15, No. 3, 03.1981, p. 224-245.

Research output: Contribution to journalArticle

@article{86d9248bd10c4f8d9bdc9499c21c4d3e,
title = "The effect of median filtering on edge location estimation",
abstract = "We study the effect of noise reduction preprocessing, specifically median filtering and averaging, on the accuracy of edge location estimation using least squares. The original edge is either a step or a linear ramp, corrupted by white Gaussian noise or binary symmetrical channel noise. The surprising conclusion is that in the case of white Gaussian noise, neither median filtering nor averaging improves the estimation accuracy. In the case of binary symmetrical channel noise, median filtering does improve the estimation accuracy for ramp edges, which are reasonable models for real-life edges.",
author = "Yang, {G. J.} and Huang, {T. S.}",
year = "1981",
month = "3",
doi = "10.1016/0146-664X(81)90057-5",
language = "English (US)",
volume = "15",
pages = "224--245",
journal = "Computer Graphics and Image Processing",
issn = "0146-664X",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - The effect of median filtering on edge location estimation

AU - Yang, G. J.

AU - Huang, T. S.

PY - 1981/3

Y1 - 1981/3

N2 - We study the effect of noise reduction preprocessing, specifically median filtering and averaging, on the accuracy of edge location estimation using least squares. The original edge is either a step or a linear ramp, corrupted by white Gaussian noise or binary symmetrical channel noise. The surprising conclusion is that in the case of white Gaussian noise, neither median filtering nor averaging improves the estimation accuracy. In the case of binary symmetrical channel noise, median filtering does improve the estimation accuracy for ramp edges, which are reasonable models for real-life edges.

AB - We study the effect of noise reduction preprocessing, specifically median filtering and averaging, on the accuracy of edge location estimation using least squares. The original edge is either a step or a linear ramp, corrupted by white Gaussian noise or binary symmetrical channel noise. The surprising conclusion is that in the case of white Gaussian noise, neither median filtering nor averaging improves the estimation accuracy. In the case of binary symmetrical channel noise, median filtering does improve the estimation accuracy for ramp edges, which are reasonable models for real-life edges.

UR - http://www.scopus.com/inward/record.url?scp=0019392776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0019392776&partnerID=8YFLogxK

U2 - 10.1016/0146-664X(81)90057-5

DO - 10.1016/0146-664X(81)90057-5

M3 - Article

AN - SCOPUS:0019392776

VL - 15

SP - 224

EP - 245

JO - Computer Graphics and Image Processing

JF - Computer Graphics and Image Processing

SN - 0146-664X

IS - 3

ER -