Texture analysis of sar sea ice imagery using gray level co-occurrence matrices

Leen Kiat Soh, Costas Tsatsoulis

Research output: Contribution to journalArticle

698 Citations (Scopus)

Abstract

This paper presents a preliminary study for mapping sea ice patterns (texture) with 100-m ERS-1 synthetic aperture radar (SAR) imagery. We used gray-level co-occurrence matrices (GLCM) to quantitatively evaluate textural parameters and representations and to determine which parameter values and representations are best for mapping sea ice texture. We conducted experiments on the quantization levels of the image and the displacement and orientation values of the GLCM by examining the effects textural descriptors such as entropy have in the representation of different sea ice textures. We showed that a complete gray-level representation of the image is not necessary for texture mapping, an eight-level quantization representation is undesirable for textural representation, and the displacement factor in texture measurements is more important than orientation. In addition, we developed three GLCM implementations and evaluated them by a supervised Bayesian classifier on sea ice textural contexts. This experiment concludes that the best GLCM implementation in representing sea ice texture is one that utilizes a range of displacement values such that both microtextures and macrotextures of sea ice can be adequately captured. These findings define the quantization, displacement, and orientation values that are the best for SAR sea ice texture analysis using GLCM.

Original languageEnglish (US)
Pages (from-to)780-795
Number of pages16
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume37
Issue number2 I
DOIs
StatePublished - Dec 1 1999

Fingerprint

Sea ice
sea ice
imagery
textures
Textures
texture
occurrences
matrix
matrices
Synthetic aperture radar
synthetic aperture radar
radar imagery
ERS-1 (ESA satellite)
analysis
classifiers
entropy
Classifiers
Entropy
experiment
Experiments

Keywords

  • Co-occurrence matrix
  • SAR
  • Sea ice, texture

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Earth and Planetary Sciences(all)

Cite this

Texture analysis of sar sea ice imagery using gray level co-occurrence matrices. / Soh, Leen Kiat; Tsatsoulis, Costas.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 37, No. 2 I, 01.12.1999, p. 780-795.

Research output: Contribution to journalArticle

@article{4ded2cc900524e1287e7f33bf43a0a16,
title = "Texture analysis of sar sea ice imagery using gray level co-occurrence matrices",
abstract = "This paper presents a preliminary study for mapping sea ice patterns (texture) with 100-m ERS-1 synthetic aperture radar (SAR) imagery. We used gray-level co-occurrence matrices (GLCM) to quantitatively evaluate textural parameters and representations and to determine which parameter values and representations are best for mapping sea ice texture. We conducted experiments on the quantization levels of the image and the displacement and orientation values of the GLCM by examining the effects textural descriptors such as entropy have in the representation of different sea ice textures. We showed that a complete gray-level representation of the image is not necessary for texture mapping, an eight-level quantization representation is undesirable for textural representation, and the displacement factor in texture measurements is more important than orientation. In addition, we developed three GLCM implementations and evaluated them by a supervised Bayesian classifier on sea ice textural contexts. This experiment concludes that the best GLCM implementation in representing sea ice texture is one that utilizes a range of displacement values such that both microtextures and macrotextures of sea ice can be adequately captured. These findings define the quantization, displacement, and orientation values that are the best for SAR sea ice texture analysis using GLCM.",
keywords = "Co-occurrence matrix, SAR, Sea ice, texture",
author = "Soh, {Leen Kiat} and Costas Tsatsoulis",
year = "1999",
month = "12",
day = "1",
doi = "10.1109/36.752194",
language = "English (US)",
volume = "37",
pages = "780--795",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2 I",

}

TY - JOUR

T1 - Texture analysis of sar sea ice imagery using gray level co-occurrence matrices

AU - Soh, Leen Kiat

AU - Tsatsoulis, Costas

PY - 1999/12/1

Y1 - 1999/12/1

N2 - This paper presents a preliminary study for mapping sea ice patterns (texture) with 100-m ERS-1 synthetic aperture radar (SAR) imagery. We used gray-level co-occurrence matrices (GLCM) to quantitatively evaluate textural parameters and representations and to determine which parameter values and representations are best for mapping sea ice texture. We conducted experiments on the quantization levels of the image and the displacement and orientation values of the GLCM by examining the effects textural descriptors such as entropy have in the representation of different sea ice textures. We showed that a complete gray-level representation of the image is not necessary for texture mapping, an eight-level quantization representation is undesirable for textural representation, and the displacement factor in texture measurements is more important than orientation. In addition, we developed three GLCM implementations and evaluated them by a supervised Bayesian classifier on sea ice textural contexts. This experiment concludes that the best GLCM implementation in representing sea ice texture is one that utilizes a range of displacement values such that both microtextures and macrotextures of sea ice can be adequately captured. These findings define the quantization, displacement, and orientation values that are the best for SAR sea ice texture analysis using GLCM.

AB - This paper presents a preliminary study for mapping sea ice patterns (texture) with 100-m ERS-1 synthetic aperture radar (SAR) imagery. We used gray-level co-occurrence matrices (GLCM) to quantitatively evaluate textural parameters and representations and to determine which parameter values and representations are best for mapping sea ice texture. We conducted experiments on the quantization levels of the image and the displacement and orientation values of the GLCM by examining the effects textural descriptors such as entropy have in the representation of different sea ice textures. We showed that a complete gray-level representation of the image is not necessary for texture mapping, an eight-level quantization representation is undesirable for textural representation, and the displacement factor in texture measurements is more important than orientation. In addition, we developed three GLCM implementations and evaluated them by a supervised Bayesian classifier on sea ice textural contexts. This experiment concludes that the best GLCM implementation in representing sea ice texture is one that utilizes a range of displacement values such that both microtextures and macrotextures of sea ice can be adequately captured. These findings define the quantization, displacement, and orientation values that are the best for SAR sea ice texture analysis using GLCM.

KW - Co-occurrence matrix

KW - SAR

KW - Sea ice, texture

UR - http://www.scopus.com/inward/record.url?scp=0033097007&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033097007&partnerID=8YFLogxK

U2 - 10.1109/36.752194

DO - 10.1109/36.752194

M3 - Article

AN - SCOPUS:0033097007

VL - 37

SP - 780

EP - 795

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 2 I

ER -