Texture analysis through a Markovian modelling and fuzzy classification: Application to urban area extraction from satellite images

Herein we propose a complete procedure to analyze and classify the texture of an image. We apply this scheme to solve a specific image processing prob lem: urban areas detection in satellite images. First we propose to analyze the texture through the modelling of the luminance field with eight differ ent chain-based models. We then derived a texture parameter from these mode ls. The effect of the lattice anisotropy is corrected by a renormalization group technique coming from statistical physics. This parameter, which take s into account local conditional variances of the image, is compared to cla ssical methods of texture analysis. Afterwards we develop a modified fuzzy Cmeans algorithm that includes an entropy term. The advantage of such an al gorithm is that the number of classes does not need to be known a priori. B esides this algorithm provides us with further information, i.e. the probab ility that a given pixel belongs to a given cluster. Finally we introduce t his information in a Markovian model of segmentation. Some results on SPOT5 simulated images, SPOT3 images and ERS1 radar images are presented. These images are provided by the French National Space Agency (CNES) and the Euro pean Space Agency (ESA).