A three-dimensional neural network model for unconstrained handwritten numeral recognition: A new approach

N. V. Subba Reddy, P. Nagabhushan

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

The paper describes a three-dimensional (3-D) neural network recognition system for conflict resolution in recognition of unconstrained handwritten numerals. This neural network classifier is a combination of modified self-organizing map (MSOM) and learning vector quantization (LVQ). The 3-D neural network recognition system has many layers of such neural network classifiers and the number of layers forms the third dimension. The Experiments are conducted employing SOM, MSOM, SOM and LVQ, and MSOM and LVQ networks. These experiments on a database of unconstrained handwritten samples show that the combination of MSOM and LVQ performs better than other networks in terms of classification, recognition and training time. The 3-D neural network eliminates the substitution error.

Original languageEnglish
Pages (from-to)511-516
Number of pages6
JournalPattern Recognition
Volume31
Issue number5
DOIs
Publication statusPublished - 01-03-1998

Fingerprint

Vector quantization
Self organizing maps
Neural networks
Classifiers
Substitution reactions
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{aeb0cae6f2474f468221d96dcddaa709,
title = "A three-dimensional neural network model for unconstrained handwritten numeral recognition: A new approach",
abstract = "The paper describes a three-dimensional (3-D) neural network recognition system for conflict resolution in recognition of unconstrained handwritten numerals. This neural network classifier is a combination of modified self-organizing map (MSOM) and learning vector quantization (LVQ). The 3-D neural network recognition system has many layers of such neural network classifiers and the number of layers forms the third dimension. The Experiments are conducted employing SOM, MSOM, SOM and LVQ, and MSOM and LVQ networks. These experiments on a database of unconstrained handwritten samples show that the combination of MSOM and LVQ performs better than other networks in terms of classification, recognition and training time. The 3-D neural network eliminates the substitution error.",
author = "{Subba Reddy}, {N. V.} and P. Nagabhushan",
year = "1998",
month = "3",
day = "1",
doi = "10.1016/S0031-3203(97)00075-7",
language = "English",
volume = "31",
pages = "511--516",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "5",

}

A three-dimensional neural network model for unconstrained handwritten numeral recognition : A new approach. / Subba Reddy, N. V.; Nagabhushan, P.

In: Pattern Recognition, Vol. 31, No. 5, 01.03.1998, p. 511-516.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A three-dimensional neural network model for unconstrained handwritten numeral recognition

T2 - A new approach

AU - Subba Reddy, N. V.

AU - Nagabhushan, P.

PY - 1998/3/1

Y1 - 1998/3/1

N2 - The paper describes a three-dimensional (3-D) neural network recognition system for conflict resolution in recognition of unconstrained handwritten numerals. This neural network classifier is a combination of modified self-organizing map (MSOM) and learning vector quantization (LVQ). The 3-D neural network recognition system has many layers of such neural network classifiers and the number of layers forms the third dimension. The Experiments are conducted employing SOM, MSOM, SOM and LVQ, and MSOM and LVQ networks. These experiments on a database of unconstrained handwritten samples show that the combination of MSOM and LVQ performs better than other networks in terms of classification, recognition and training time. The 3-D neural network eliminates the substitution error.

AB - The paper describes a three-dimensional (3-D) neural network recognition system for conflict resolution in recognition of unconstrained handwritten numerals. This neural network classifier is a combination of modified self-organizing map (MSOM) and learning vector quantization (LVQ). The 3-D neural network recognition system has many layers of such neural network classifiers and the number of layers forms the third dimension. The Experiments are conducted employing SOM, MSOM, SOM and LVQ, and MSOM and LVQ networks. These experiments on a database of unconstrained handwritten samples show that the combination of MSOM and LVQ performs better than other networks in terms of classification, recognition and training time. The 3-D neural network eliminates the substitution error.

UR - http://www.scopus.com/inward/record.url?scp=0032064193&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032064193&partnerID=8YFLogxK

U2 - 10.1016/S0031-3203(97)00075-7

DO - 10.1016/S0031-3203(97)00075-7

M3 - Article

AN - SCOPUS:0032064193

VL - 31

SP - 511

EP - 516

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 5

ER -