Neural-network classifiers for recognizing total unconstrained handwritten numerals

Research output: Contribution to journalArticle

126 Citations (Scopus)

Abstract

Artificial neural networks have been recognized as a powerful tool for pattern classification problems, but a number of researchers have also suggested that straightforward neural-network approaches to pattern recognition are largely inadequate for difficult problems such as handwritten numeral recognition. In this paper, we present three sophisticated neural-network classifiers to solve complex pattern recognition problems: multiple multilayer perceptron (MLP) classifier, hidden Markov model (HMM)/MLP hybrid classifier, and structure-adaptive self-organizing map (SOM) classifier. In order to verify the superiority of the proposed classifiers, experiments were performed with the unconstrained handwritten numeral database of Concordia University, Montreal, Canada. The three methods have produced 97.35%, 96.55%, and 96.05% of the recognition rates, respectively, which are better than those of several previous methods reported in the literature on the same database.

Original languageEnglish
Pages (from-to)43-53
Number of pages11
JournalIEEE Transactions on Neural Networks
Volume8
Issue number1
Publication statusPublished - 1997 Dec 1

Fingerprint

Numeral
Classifiers
Classifier
Neural Networks
Neural networks
Pattern recognition
Multilayer neural networks
Perceptron
Pattern Recognition
Multilayer
Pattern Classification
Self organizing maps
Self-organizing Map
Hidden Markov models
Classification Problems
Markov Model
Artificial Neural Network
Verify
Experiment
Experiments

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Hardware and Architecture

Cite this

@article{83caeeb6e02f4785b70c3e1ffa801d8b,
title = "Neural-network classifiers for recognizing total unconstrained handwritten numerals",
abstract = "Artificial neural networks have been recognized as a powerful tool for pattern classification problems, but a number of researchers have also suggested that straightforward neural-network approaches to pattern recognition are largely inadequate for difficult problems such as handwritten numeral recognition. In this paper, we present three sophisticated neural-network classifiers to solve complex pattern recognition problems: multiple multilayer perceptron (MLP) classifier, hidden Markov model (HMM)/MLP hybrid classifier, and structure-adaptive self-organizing map (SOM) classifier. In order to verify the superiority of the proposed classifiers, experiments were performed with the unconstrained handwritten numeral database of Concordia University, Montreal, Canada. The three methods have produced 97.35{\%}, 96.55{\%}, and 96.05{\%} of the recognition rates, respectively, which are better than those of several previous methods reported in the literature on the same database.",
author = "Sung-Bae Cho",
year = "1997",
month = "12",
day = "1",
language = "English",
volume = "8",
pages = "43--53",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "1",

}

Neural-network classifiers for recognizing total unconstrained handwritten numerals. / Cho, Sung-Bae.

In: IEEE Transactions on Neural Networks, Vol. 8, No. 1, 01.12.1997, p. 43-53.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural-network classifiers for recognizing total unconstrained handwritten numerals

AU - Cho, Sung-Bae

PY - 1997/12/1

Y1 - 1997/12/1

N2 - Artificial neural networks have been recognized as a powerful tool for pattern classification problems, but a number of researchers have also suggested that straightforward neural-network approaches to pattern recognition are largely inadequate for difficult problems such as handwritten numeral recognition. In this paper, we present three sophisticated neural-network classifiers to solve complex pattern recognition problems: multiple multilayer perceptron (MLP) classifier, hidden Markov model (HMM)/MLP hybrid classifier, and structure-adaptive self-organizing map (SOM) classifier. In order to verify the superiority of the proposed classifiers, experiments were performed with the unconstrained handwritten numeral database of Concordia University, Montreal, Canada. The three methods have produced 97.35%, 96.55%, and 96.05% of the recognition rates, respectively, which are better than those of several previous methods reported in the literature on the same database.

AB - Artificial neural networks have been recognized as a powerful tool for pattern classification problems, but a number of researchers have also suggested that straightforward neural-network approaches to pattern recognition are largely inadequate for difficult problems such as handwritten numeral recognition. In this paper, we present three sophisticated neural-network classifiers to solve complex pattern recognition problems: multiple multilayer perceptron (MLP) classifier, hidden Markov model (HMM)/MLP hybrid classifier, and structure-adaptive self-organizing map (SOM) classifier. In order to verify the superiority of the proposed classifiers, experiments were performed with the unconstrained handwritten numeral database of Concordia University, Montreal, Canada. The three methods have produced 97.35%, 96.55%, and 96.05% of the recognition rates, respectively, which are better than those of several previous methods reported in the literature on the same database.

UR - http://www.scopus.com/inward/record.url?scp=0030784110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030784110&partnerID=8YFLogxK

M3 - Article

C2 - 18255609

AN - SCOPUS:0030784110

VL - 8

SP - 43

EP - 53

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 1

ER -