tanbul 2004 
TEXTURE FEATURE EXTRACTION FOR CLASSIFICATION OF REMOTE SENSING 
DATA USING WAVELET DECOMPOSITION: A COMPARATIVE STUDY 
L. A. Ruiz; A. Fdez-Sarría; J.A. Recio 
Dept. of Cartographic Engineering, Geodesy and Photogrammetry. Politechnic University of Valeneia. 
Camino de Vera s/n 46022-Valencia (Spain) — (laruiz, afernan, jrecio@cgf.upv.es) 
KEY WORDS: Texture classification, multiresolution analysis, wavelets, urban, vegetation 
ABSTRACT: 
The extraction of texture features from high resolution remote sensing imagery provides a complementary source of data for those 
applications in which the spectral information is not sufficient for identification or classification of spectrally heterogeneous 
landscape units. However, there is a wide range of texture analysis techniques that are used with different criteria for feature 
extraction: statistical methods (grey level coocurrence matrix, semivariogram analysis); filter techniques (energy filters, Gabor 
filters); or the most recent techniques based on wavelet decomposition. The combination of parameters that optimize a method for a 
specific application should be decided when these techniques are used. These parameters include the neighbourhood size, the 
distance between pixels, the type of filter or mother wavelet used, the frequency or the standard deviation used to create the Gabor 
filters, etc. The combination of parameters and the texture method used is expected to be key in the success and efficiency of these 
techniques for a particular application. 
In this study, we analyze several texture methods applied to the classification of remote sensing images with different types of 
landscapes, as well as the optimal combination of parameters for each group of data. For this purpose, we created a database with 
high resolution satellite and aerial images from two types of env 
ironments, representing two of the main applications of texture 
analysis in remote sensing: Urban and forestry. The texture classes defined in urban applications involve heterogeneity and 
symmetry, while in forest applications is important to know the ty 
application determines the technique and the combination of p 
pe and density of vegetation. The results show that the type of 
arameters to be used for optimizing accuracy. The combination of 
texture methods and spectral information improves the results of classification. Finally, some specific methods to correct the border 
effect should be developped before these techniques can be applied in practice. 
1. INTRODUCTION 
Multispectral information provided by airborne and satellite 
Sensors is succesfully used for creating and updating 
cartography for forest and agriculture uses, as well as for 
monitoring urban sprawl. This information is valuable as a 
complement to the field data and the more traditional manual 
interpretation of aerial photographs, allowing for an increase in 
the efficiency of the processes by partially automatizing certain 
tasks, thus reducing costs of field data collection and improving 
the updating frequency due to the regularity of quality imagery 
data. 
In forestry and urban studies, multispectral classification 
techniques provide suitable results when the classes defined 
fepresent structural and spectral homogeneous units, provided 
that the spectral response pattern of each class is sufficiently 
specific. This is the case of mountain areas where there are 
dense forests with uniform growth and a predominance of one 
er few species. However, mediterranean ecosystems present a 
Wide structural and botanical diversity. A similar situation 
occurs in most of the peripheral urban areas, where there is a 
Strong structural diversity and, consequently, an important 
Spectral variability in the urban landscape units. This makes the 
Process of classification using only spectral information more 
difficult, and some methods for the extraction of structural 
information from each type of unit are required. 
Texture analysis offers interesting possibilities to characterize 
the Structural heterogeneity of classes. The texture of an image 
IS related to the spatial distribution of the intensity values in the 
Mage, and as such contains information regarding contrast, 
uniformity, rugosity, regularity, etc. A considerable number of 
quantitative texture features can be extracted from images using 
different methodologies in order to characterize these 
properties, and then can be used to classify pixels following 
analogous processes as with spectral classifications. 
Many texture comparative studies can be found in the literature, 
usually carried out by employing standard image databases for 
the testing process. However, due to the lack of a widely 
accepted benchmark, all experimental results should be 
considered to be applicable only to the reported setup. Using 
images from the same database gives no guarantee of obtaining 
comparable experimental results (Ojala et al., 2002). 
In this article we describe the application of several texture 
feature extraction approaches to classify different images from 
‘two main environments: forest and urban landscapes. The 
fundamental goals of this study were: 
* To compare and evaluate four different approaches for 
the extraction of texture features applied to the 
classification of a variety of images in different 
environments, analyzing and assessing the different 
methodological parameters involved in the process. 
To study the potential of these techniques in order to 
classify (1) mediterranean forest landscape units with 
different density and types of vegetation, and (2) urban 
sprawl units. 
To assess the potential sinergy of the combination of 
texture and spectral data from high resolution satellite 
images, in order to classify complex landscapes. 
1109