Nonlinear wave metric and its CNN implementation for object classification

István Szatmári, Csaba Rekeczky, T. Roska

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

In this paper a nonlinear wave metric is introduced for object classification. It is shown that the choice of a metric is a nontrivial problem since it is easy to give examples when well-known distance measures, such as Hamming, Hausdorff, and Nonlinear Hausdorff metrics are completely inadequate for this classification. As an alternative a generalized theorem is proposed that includes the previous metrics as special cases. It is based on nonlinear wave propagation and defines a computational framework that is well-suited for parallel array processors. In this study we investigate different Cellular Neural Network (CNN) architectures and solutions for the proposed metric and analyze its VLSI implementation complexity.

Original languageEnglish
Pages (from-to)437-447
Number of pages11
JournalJournal of VLSI Signal Processing Systems for Signal, Image, and Video Technology
Volume23
Issue number2
Publication statusPublished - 1999

Fingerprint

Object Classification
Cellular neural networks
Nonlinear Waves
Cellular Networks
Neural Networks
Metric
Parallel processing systems
Network architecture
Wave propagation
Nonlinear Wave Propagation
Hausdorff Metric
Distance Measure
Network Architecture
Alternatives
Theorem

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Nonlinear wave metric and its CNN implementation for object classification. / Szatmári, István; Rekeczky, Csaba; Roska, T.

In: Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, Vol. 23, No. 2, 1999, p. 437-447.

Research output: Contribution to journalArticle

@article{f2a5fd9f8aff44168170f0f2af7babd2,
title = "Nonlinear wave metric and its CNN implementation for object classification",
abstract = "In this paper a nonlinear wave metric is introduced for object classification. It is shown that the choice of a metric is a nontrivial problem since it is easy to give examples when well-known distance measures, such as Hamming, Hausdorff, and Nonlinear Hausdorff metrics are completely inadequate for this classification. As an alternative a generalized theorem is proposed that includes the previous metrics as special cases. It is based on nonlinear wave propagation and defines a computational framework that is well-suited for parallel array processors. In this study we investigate different Cellular Neural Network (CNN) architectures and solutions for the proposed metric and analyze its VLSI implementation complexity.",
author = "Istv{\'a}n Szatm{\'a}ri and Csaba Rekeczky and T. Roska",
year = "1999",
language = "English",
volume = "23",
pages = "437--447",
journal = "Journal of Signal Processing Systems",
issn = "1939-8018",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Nonlinear wave metric and its CNN implementation for object classification

AU - Szatmári, István

AU - Rekeczky, Csaba

AU - Roska, T.

PY - 1999

Y1 - 1999

N2 - In this paper a nonlinear wave metric is introduced for object classification. It is shown that the choice of a metric is a nontrivial problem since it is easy to give examples when well-known distance measures, such as Hamming, Hausdorff, and Nonlinear Hausdorff metrics are completely inadequate for this classification. As an alternative a generalized theorem is proposed that includes the previous metrics as special cases. It is based on nonlinear wave propagation and defines a computational framework that is well-suited for parallel array processors. In this study we investigate different Cellular Neural Network (CNN) architectures and solutions for the proposed metric and analyze its VLSI implementation complexity.

AB - In this paper a nonlinear wave metric is introduced for object classification. It is shown that the choice of a metric is a nontrivial problem since it is easy to give examples when well-known distance measures, such as Hamming, Hausdorff, and Nonlinear Hausdorff metrics are completely inadequate for this classification. As an alternative a generalized theorem is proposed that includes the previous metrics as special cases. It is based on nonlinear wave propagation and defines a computational framework that is well-suited for parallel array processors. In this study we investigate different Cellular Neural Network (CNN) architectures and solutions for the proposed metric and analyze its VLSI implementation complexity.

UR - http://www.scopus.com/inward/record.url?scp=0343628804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0343628804&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0343628804

VL - 23

SP - 437

EP - 447

JO - Journal of Signal Processing Systems

JF - Journal of Signal Processing Systems

SN - 1939-8018

IS - 2

ER -