Evaluation of morphological multifractal models for texture classification

In this paper we further investigate multifractal models based on morphological dilation and erosion. Multifractal spectrum, as a signature of multifractal behavior of the signal, is inspected regarding its most significant parameters: local dimension scales and boxes used for calculation of box-counting (global) dimensions. Extensive tests done within this research provide directions toward selection of these parameters concerning classification of textural images. It is shown that the adequate choice of parameters of the multifractal model provides significant improvement of the classification.