Texture primitives description and segmentation using variography and mathematical morphology

In this paper, we propose a novel method of optimizing texture primitives description and segmentation using variography. Indeed, successful textural analysis relies on the careful selection of the adapted window size. The variogram is essentially a "variance of differences" in the values as a function of the separation distance. This variance therefore changes as the separation distance increases where repetitive structures are described as hole-effects. We used the local minima (hole-effects) to find size, shape an orientation of unit pattern of image textures and thus to determine the optimal structuring element which is used in mathematical morphological texture analysis. Some of Brodatz's natural texture images have been used for evaluating the performance of this method. The structuring elements found are well adapted for the characterization and discrimination of the texture aspects of images. Furthermore, we performed a textural segmentation using the variogram characteristics. Promising results are obtained and presented.