Characterization of the Texture of Digital Images by Variography Approach: An Application to the Classification of SAR Images

Characterization of the Texture of Digital Images by Variography Approach: An Application to the Classification of SAR Images This paper presents a method of texture modelling using geostatistic theory. From variographics abacus and variogram proprieties, fractal and exponential models have been used to characterize Brodatz textures. In this approach, a texture is modelled by a vector called feature vector whose components are parameters characterizing the experimental variogram, notably the “Slope”, the “Range”, the “Landing” and the “Fractal Dimension (FD)”.