Gabor filter design for multiple texture segmentation

Thomas P. Weldon, William Evan Higgins, Dennis F. Dunn

Research output: Contribution to journalArticle

74 Citations (Scopus)

Abstract

A method is presented for the design of a single Gabor filter for the segmentation of multitextured images. Earlier methods were limited to filters designed for one or two textures or to filters selected from a predetermined filter bank. Our proposed method yields new insight into the design of Gabor filters for segmenting multitextured images and lays an essential foundation for the design of multiple Gabor filters. In the method, Rician statistics of filtered textures at two different Gabor-filter envelope scales are used to efficiently generate probability density estimates for each filtered texture over an extensive set of candidate filter parameters. Variable degrees of postfiltering and the accompanying effect on postfilter output statistics are also included in the design procedure. The result is a unified framework that analytically relates the texture power spectra, Gabor-filter parameters, postfiltering effects, and image-segmentation error. Finally, the resulting filter design is based on all constituent textures and is not constrained to a limited set of candidate filters.

Original languageEnglish (US)
Article number16125
Pages (from-to)2852-2863
Number of pages12
JournalOptical Engineering
Volume35
Issue number10
DOIs
StatePublished - Jan 1 1996

Fingerprint

Gabor filters
textures
Textures
filters
Statistics
statistics
Filter banks
Power spectrum
Image segmentation
power spectra
envelopes
output
estimates

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Engineering(all)

Cite this

Weldon, Thomas P. ; Higgins, William Evan ; Dunn, Dennis F. / Gabor filter design for multiple texture segmentation. In: Optical Engineering. 1996 ; Vol. 35, No. 10. pp. 2852-2863.
@article{2694e8ed43d24c25a81ad73b76c11bbe,
title = "Gabor filter design for multiple texture segmentation",
abstract = "A method is presented for the design of a single Gabor filter for the segmentation of multitextured images. Earlier methods were limited to filters designed for one or two textures or to filters selected from a predetermined filter bank. Our proposed method yields new insight into the design of Gabor filters for segmenting multitextured images and lays an essential foundation for the design of multiple Gabor filters. In the method, Rician statistics of filtered textures at two different Gabor-filter envelope scales are used to efficiently generate probability density estimates for each filtered texture over an extensive set of candidate filter parameters. Variable degrees of postfiltering and the accompanying effect on postfilter output statistics are also included in the design procedure. The result is a unified framework that analytically relates the texture power spectra, Gabor-filter parameters, postfiltering effects, and image-segmentation error. Finally, the resulting filter design is based on all constituent textures and is not constrained to a limited set of candidate filters.",
author = "Weldon, {Thomas P.} and Higgins, {William Evan} and Dunn, {Dennis F.}",
year = "1996",
month = "1",
day = "1",
doi = "10.1117/1.600971",
language = "English (US)",
volume = "35",
pages = "2852--2863",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "10",

}

Gabor filter design for multiple texture segmentation. / Weldon, Thomas P.; Higgins, William Evan; Dunn, Dennis F.

In: Optical Engineering, Vol. 35, No. 10, 16125, 01.01.1996, p. 2852-2863.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Gabor filter design for multiple texture segmentation

AU - Weldon, Thomas P.

AU - Higgins, William Evan

AU - Dunn, Dennis F.

PY - 1996/1/1

Y1 - 1996/1/1

N2 - A method is presented for the design of a single Gabor filter for the segmentation of multitextured images. Earlier methods were limited to filters designed for one or two textures or to filters selected from a predetermined filter bank. Our proposed method yields new insight into the design of Gabor filters for segmenting multitextured images and lays an essential foundation for the design of multiple Gabor filters. In the method, Rician statistics of filtered textures at two different Gabor-filter envelope scales are used to efficiently generate probability density estimates for each filtered texture over an extensive set of candidate filter parameters. Variable degrees of postfiltering and the accompanying effect on postfilter output statistics are also included in the design procedure. The result is a unified framework that analytically relates the texture power spectra, Gabor-filter parameters, postfiltering effects, and image-segmentation error. Finally, the resulting filter design is based on all constituent textures and is not constrained to a limited set of candidate filters.

AB - A method is presented for the design of a single Gabor filter for the segmentation of multitextured images. Earlier methods were limited to filters designed for one or two textures or to filters selected from a predetermined filter bank. Our proposed method yields new insight into the design of Gabor filters for segmenting multitextured images and lays an essential foundation for the design of multiple Gabor filters. In the method, Rician statistics of filtered textures at two different Gabor-filter envelope scales are used to efficiently generate probability density estimates for each filtered texture over an extensive set of candidate filter parameters. Variable degrees of postfiltering and the accompanying effect on postfilter output statistics are also included in the design procedure. The result is a unified framework that analytically relates the texture power spectra, Gabor-filter parameters, postfiltering effects, and image-segmentation error. Finally, the resulting filter design is based on all constituent textures and is not constrained to a limited set of candidate filters.

UR - http://www.scopus.com/inward/record.url?scp=0001974282&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0001974282&partnerID=8YFLogxK

U2 - 10.1117/1.600971

DO - 10.1117/1.600971

M3 - Article

AN - SCOPUS:0001974282

VL - 35

SP - 2852

EP - 2863

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 10

M1 - 16125

ER -