Superparamagnetic segmentation by excitable neural systems

Juan P. Neirotti, Samuel M. Kurcbart, Nestor Caticha
2003 Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics  
Magnetic modeling for clustering or segmentation purposes can either associate the image data to external quenched fields or to the interactions among a set of auxiliary variables. The latter gives rise to superparamagnetic segmentation and is usually done with Potts systems. We have used the superparamagnetic clustering technique to segment images, with the aid of different associated systems. Results using Potts model are comparable to those obtained using excitable FitzHugh-Nagumo and
more » ... Lecar model neurons. Interactions between the associated system components are a function of the difference of luminosity on a gray scale of neighbor pixels and the difference of membrane potential.
doi:10.1103/physreve.68.031911 pmid:14524807 fatcat:xa4f7kkp5bguren3fjhtu46a6u