English

Pattern recognition at different scales: a statistical perspective

Statistical Mechanics 2015-06-19 v1 Disordered Systems and Neural Networks

Abstract

In this paper we borrow concepts from Information Theory and Statistical Mechanics to perform a pattern recognition procedure on a set of x-ray hazelnut images. We identify two relevant statistical scales, whose ratio affects the performance of a machine learning algorithm based on statistical observables, and discuss the dependence of such scales on the image resolution. Finally, by averaging the performance of a Support Vector Machines algorithm over a set of training samples, we numerically verify the predicted onset of an optimal scale of resolution, at which the pattern recognition is favoured.

Keywords

Cite

@article{arxiv.1404.2638,
  title  = {Pattern recognition at different scales: a statistical perspective},
  author = {Matteo Colangeli and Francesco Rugiano and Eros Pasero},
  journal= {arXiv preprint arXiv:1404.2638},
  year   = {2015}
}
R2 v1 2026-06-22T03:47:27.400Z