The evaluation of feature extraction criteria applied to neural network classifiers

W. Utschick, P. Nachbar, C. Knobloch, A. Schuler, J. A. Nossek

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Feature extraction is a crucial part of classijicationprocedures. In this paper we present an approach, how to utilize feature extraction criteria to predict the potential efficiency of a neural network classijiel: Statistical and geometrical criteria are introduced for analysis. The complete system of our research consists of a class of generalized Hough-Transformations for feature extraction and a subsequent neural network. The neural network performs the classijication based on respective features. For an example we concentrated on a pattern recognition problem - The classijication of handwritten numerals. As a result of our work we assign two feature extraction criteria to the employed network for a significant estimation of its eflciency.

Original languageEnglish
Title of host publicationProceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995
PublisherIEEE Computer Society
Pages315-318
Number of pages4
ISBN (Electronic)0818671289
DOIs
StatePublished - 1995
Event3rd International Conference on Document Analysis and Recognition, ICDAR 1995 - Montreal, Canada
Duration: 14 Aug 199516 Aug 1995

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume1
ISSN (Print)1520-5363

Conference

Conference3rd International Conference on Document Analysis and Recognition, ICDAR 1995
Country/TerritoryCanada
CityMontreal
Period14/08/9516/08/95

Keywords

  • Classijication
  • Feature extraction
  • Statistical criteria

Fingerprint

Dive into the research topics of 'The evaluation of feature extraction criteria applied to neural network classifiers'. Together they form a unique fingerprint.

Cite this