Multifractal techniques for texture classification and image filtering

This paper advocates a method for image classification based on new multifractal descriptors. It is explained in context of existing monofractal and multifractal techniques from literature. Employed multifractal descriptors are based on monofractal blanket method from literature and represented by multifractal spectrum. Generalization of blanket method results in three new multifractal methods based on interpretation of the image. All proposed generalizations provide better classification results than monofractal blanket method. Additionally, a new adaptive technique using multifractal model is presented for low-pass image filtering with edges and textural regions preservation. Quantitative evaluation on natural images shows better filtering results regarding edge preservation than non-adaptive filters.