Multifractals, texture, and image analysis

Abstract

Image analysis using texture and multifractal paradigms is addressed. Multifractal theory and its application to image description are discussed, and it is shown that this approach allows the discrete signal to be worked on directly. A system for texture classification that is based on a learning scheme and does not make use of any a priori model is introduced. Image segmentation is then considered, and the notion of mixed classes, which allows accurate detection of texture boundaries on complex images, is introduced.<>