Алгоритмы фрактального анализа изображений

Abstract

The applicability of the method of modified fractal signature to classify images of two different application domains is considered. The method is based on the calculation of the Minkovsky dimension for a fractal surface that is the graph of the gray-level function of the image. It is well known that for nonempty bounded sets in Euclidean space the Minkovsky dimension coincides with the capacity one, but it can be calculated more effectively. The given examples show that the method allows us to obtain reliable results for classes of images under consideration.