Pattern recognition at different scales: a statistical perspective

DOI10.1016/J.CHAOS.2013.10.006zbMATH Open1348.68210arXiv1404.2638OpenAlexW2025104370MaRDI QIDQ336155FDOQ336155

Authors: M. Colangeli, Francesco Rugiano, Eros Pasero 

Publication date: 10 November 2016

Published in: Chaos, Solitons and Fractals (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1404.2638

Recommendations

• scientific article; zbMATH DE number 3862476
• scientific article; zbMATH DE number 3913717
• scientific article; zbMATH DE number 1166376
• Information approach to the problems of pattern recognition
• SIMBAD: emergence of pattern similarity

Mathematics Subject Classification ID

Applications of statistics (62P99) Pattern recognition, speech recognition (68T10) Computing methodologies for image processing (68U10)

Cites Work

• Support-vector networks
• Title not available (Why is that?)
• On Information and Sufficiency
• Title not available (Why is that?)
• Title not available (Why is that?)
• Information theoretic measures for clusterings comparison: variants, properties, normalization and correction for chance
• Title not available (Why is that?)
• An invariant form for the prior probability in estimation problems
• Information Theory and Statistical Mechanics
• Title not available (Why is that?)
• Karl Pearson and the Chi-Squared Test
• Title not available (Why is that?)
• Markov Processes and the H-Theorem
• Title not available (Why is that?)
• On measuring the distance between histograms,
• Image processing with neural networks -- a review
• The simplest maximum entropy model for collective behavior in a neural network

Cited In (4)

• Image characterization by fractal descriptors in variational mode decomposition domain: application to brain magnetic resonance
• Pattern recognition in non-Kolmogorovian structures
• Recognition of chain-coded patches with statistical methods
• Title not available (Why is that?)

This page was built for publication: Pattern recognition at different scales: a statistical perspective

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q336155)