A Multifractal Approach for Classification of Sar Image
نویسنده
چکیده
Fractal dimension has been found not suitable to be used solely in classifying natural earth terrain. This is due to the fact that surfaces with different texture may portray similar fractal dimensions. Evertsz and Mandelbrot [Evertsz, et. al. 1992] suggested that multifractal dimension may be a more appropriate parameter than fractal dimension in describing geometrical properties of a fractal set. In this paper, a study on the relation of multifractal dimensions with window size has been carried out and the multifractal dimensions are used to classify a C-band HH polarization SAR image of Alor Setar area, Kedah, into three landuse classes, and an X-band SAR image of the Kennedy Space Centre, Florida, into two landuse classes. The modified fractal dimension has also been applied on both the images. Comparison is made between the classification results using multifractal dimensions and modified fractal dimension over the two images, respectively. The multifractal dimensions have shown encouraging classification results.
منابع مشابه
Palarimetric Synthetic Aperture Radar Image Classification using Bag of Visual Words Algorithm
Land cover is defined as the physical material of the surface of the earth, including different vegetation covers, bare soil, water surface, various urban areas, etc. Land cover and its changes are very important and influential on the Earth and life of living organisms, especially human beings. Land cover change monitoring is important for protecting the ecosystem, forests, farmland, open spac...
متن کاملOptimum Ensemble Classification for Fully Polarimetric SAR Data Using Global-Local Classification Approach
In this paper, a proposed ensemble classification for fully polarimetric synthetic aperture radar (PolSAR) data using a global-local classification approach is presented. In the first step, to perform the global classification, the training feature space is divided into a specified number of clusters. In the next step to carry out the local classification over each of these clusters, which cont...
متن کاملMicrowave Imaging Using SAR
Polarimetric Synthetic Aperture Radar (Pol.-SAR) allows us to implement the recognition and classification of radar targets. This article investigates the arrangement of scatterers by SAR data and proposes a new Look-up Table of Region (LTR). This look-up table is based on the combination of (entropy H/Anisotropy A) and (Anisotropy A/scattering mechanism α), which has not been reported up now. ...
متن کاملApplication of Multifractal Analasys for Image Classification and Denoising
Fractal approach is successfully implemented in many applications within 2D signal processing. Fractal synthetical concept is applied for image compression with high compression ratios while fractal and multifractal descriptors provide classification of textural images with high occuracy. Various multifractal models are presented in literature. This paper summarizes them and illustrates new mul...
متن کاملNatural Surface Characterization by Multifractals
This paper deals with multifractal theory applied to image analysis. Multifractals show many interesting peculiarities in the characterization of textured surfaces. In the paper, a method for the computation of multifractal parameters is proposed, together with some application results. Moreover, results are shown that depict the exploitation of such features in a data-fusion environment for SA...
متن کامل