A study of lacunarity-based texture analysis approaches to improve urban image classification

Soe Myint, Nina Lam

Research output: Contribution to journalArticle

60 Citations (Scopus)

Abstract

The traditional spectral based classifiers are normally considered ineffective in digitally classifying urban land-use and land-cover classes from high-resolution remotely sensed data due to the lack of consideration of images' spatial properties. To identify the complex arrangements of urban features in high-resolution image data, the texture information contained in a group of pixels needs to be considered. This paper discusses the concept of lacunarity and the use of two lacunarity estimation methods (i.e., binary, gray scale) in texture analysis and classification of urban images. Lacunarity has been introduced to characterize different texture appearances, which may share the same fractal dimension value. Lacunarity measures the distribution of gap sizes: Low lacunarity geometric objects are homogeneous because all gap sizes are the same, whereas high lacunarity objects are heterogeneous. Using different moving windows (i.e., 13 × 13, 21 × 21, 29 × 29), the above lacunarity methods were employed to classify urban features and to observe the effects of the size of moving windows in characterizing urban texture features. Results from this study show that traditional spectral based classification approach is inaccurate in classifying urban land categories from high-resolution image data, with an accuracy of 55%, whereas lacunarity approaches can be used to improve urban classification accuracy dramatically to 92%.

Original languageEnglish (US)
Pages (from-to)501-523
Number of pages23
JournalComputers, Environment and Urban Systems
Volume29
Issue number5 SPEC. ISS.
DOIs
StatePublished - Sep 2005
Externally publishedYes

Fingerprint

image classification
texture
image resolution
land use
estimation method
pixel
land cover
lack
analysis
Values
Group

Keywords

  • Lacunarity
  • Texture
  • Urban

ASJC Scopus subject areas

  • Ecological Modeling
  • Environmental Science(all)
  • Geography, Planning and Development

Cite this

A study of lacunarity-based texture analysis approaches to improve urban image classification. / Myint, Soe; Lam, Nina.

In: Computers, Environment and Urban Systems, Vol. 29, No. 5 SPEC. ISS., 09.2005, p. 501-523.

Research output: Contribution to journalArticle

@article{65a0b77ea1484aeea77f624b8ae4863c,
title = "A study of lacunarity-based texture analysis approaches to improve urban image classification",
abstract = "The traditional spectral based classifiers are normally considered ineffective in digitally classifying urban land-use and land-cover classes from high-resolution remotely sensed data due to the lack of consideration of images' spatial properties. To identify the complex arrangements of urban features in high-resolution image data, the texture information contained in a group of pixels needs to be considered. This paper discusses the concept of lacunarity and the use of two lacunarity estimation methods (i.e., binary, gray scale) in texture analysis and classification of urban images. Lacunarity has been introduced to characterize different texture appearances, which may share the same fractal dimension value. Lacunarity measures the distribution of gap sizes: Low lacunarity geometric objects are homogeneous because all gap sizes are the same, whereas high lacunarity objects are heterogeneous. Using different moving windows (i.e., 13 × 13, 21 × 21, 29 × 29), the above lacunarity methods were employed to classify urban features and to observe the effects of the size of moving windows in characterizing urban texture features. Results from this study show that traditional spectral based classification approach is inaccurate in classifying urban land categories from high-resolution image data, with an accuracy of 55{\%}, whereas lacunarity approaches can be used to improve urban classification accuracy dramatically to 92{\%}.",
keywords = "Lacunarity, Texture, Urban",
author = "Soe Myint and Nina Lam",
year = "2005",
month = "9",
doi = "10.1016/j.compenvurbsys.2005.01.007",
language = "English (US)",
volume = "29",
pages = "501--523",
journal = "Computers, Environment and Urban Systems",
issn = "0198-9715",
publisher = "Elsevier Limited",
number = "5 SPEC. ISS.",

}

TY - JOUR

T1 - A study of lacunarity-based texture analysis approaches to improve urban image classification

AU - Myint, Soe

AU - Lam, Nina

PY - 2005/9

Y1 - 2005/9

N2 - The traditional spectral based classifiers are normally considered ineffective in digitally classifying urban land-use and land-cover classes from high-resolution remotely sensed data due to the lack of consideration of images' spatial properties. To identify the complex arrangements of urban features in high-resolution image data, the texture information contained in a group of pixels needs to be considered. This paper discusses the concept of lacunarity and the use of two lacunarity estimation methods (i.e., binary, gray scale) in texture analysis and classification of urban images. Lacunarity has been introduced to characterize different texture appearances, which may share the same fractal dimension value. Lacunarity measures the distribution of gap sizes: Low lacunarity geometric objects are homogeneous because all gap sizes are the same, whereas high lacunarity objects are heterogeneous. Using different moving windows (i.e., 13 × 13, 21 × 21, 29 × 29), the above lacunarity methods were employed to classify urban features and to observe the effects of the size of moving windows in characterizing urban texture features. Results from this study show that traditional spectral based classification approach is inaccurate in classifying urban land categories from high-resolution image data, with an accuracy of 55%, whereas lacunarity approaches can be used to improve urban classification accuracy dramatically to 92%.

AB - The traditional spectral based classifiers are normally considered ineffective in digitally classifying urban land-use and land-cover classes from high-resolution remotely sensed data due to the lack of consideration of images' spatial properties. To identify the complex arrangements of urban features in high-resolution image data, the texture information contained in a group of pixels needs to be considered. This paper discusses the concept of lacunarity and the use of two lacunarity estimation methods (i.e., binary, gray scale) in texture analysis and classification of urban images. Lacunarity has been introduced to characterize different texture appearances, which may share the same fractal dimension value. Lacunarity measures the distribution of gap sizes: Low lacunarity geometric objects are homogeneous because all gap sizes are the same, whereas high lacunarity objects are heterogeneous. Using different moving windows (i.e., 13 × 13, 21 × 21, 29 × 29), the above lacunarity methods were employed to classify urban features and to observe the effects of the size of moving windows in characterizing urban texture features. Results from this study show that traditional spectral based classification approach is inaccurate in classifying urban land categories from high-resolution image data, with an accuracy of 55%, whereas lacunarity approaches can be used to improve urban classification accuracy dramatically to 92%.

KW - Lacunarity

KW - Texture

KW - Urban

UR - http://www.scopus.com/inward/record.url?scp=21044452190&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21044452190&partnerID=8YFLogxK

U2 - 10.1016/j.compenvurbsys.2005.01.007

DO - 10.1016/j.compenvurbsys.2005.01.007

M3 - Article

VL - 29

SP - 501

EP - 523

JO - Computers, Environment and Urban Systems

JF - Computers, Environment and Urban Systems

SN - 0198-9715

IS - 5 SPEC. ISS.

ER -