2001/07/14 by A. Turiel, N. Parga
Physics and Astronomy · #cond-mat.stat-mech #cond-mat.dis-nn
published as Neural Computation {\bf 12}, 763-793 (2000) · 41 pages, 8 figures, LaTeX
arxiv created 2001/07/14 · arxiv updated 2009/11/30
We present a formalism that leads very naturally to a hierarchical description of the different contrast structures in images, providing precise definitions of sharp edges and other texture components. Within this formalism, we achieve a decomposition of pixels of the image in sets, the fractal components of the image, such that each set only contains points characterized by a fixed stregth of the singularity of the contrast gradient in its neighborhood. A crucial role in this description of images is played by the behavior of contrast differences under changes in scale. Contrary to naive scaling ideas where the image is thought to have uniform transformation properties \citeFie87, each of these fractal components has its own transformation law and scaling exponents. A conjecture on their biological relevance is also given.