DocumentCode :
1287261
Title :
Neural-network classifiers for recognizing totally unconstrained handwritten numerals
Author :
Cho, Sung-Bae
Author_Institution :
Dept. of Comput. Sci., Yonsei Univ., Seoul, South Korea
Volume :
8
Issue :
1
fYear :
1997
fDate :
1/1/1997 12:00:00 AM
Firstpage :
43
Lastpage :
53
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
Keywords :
hidden Markov models; image classification; multilayer perceptrons; optical character recognition; self-organising feature maps; HMM/MLP hybrid classifier; SOM classifier; hidden Markov model hybrid classifier; multiple multilayer perceptron classifier; neural-network classifiers; pattern classification; structure-adaptive self-organizing map; totally unconstrained handwritten numeral recognition; unconstrained handwritten numeral database; Artificial neural networks; Handwriting recognition; Hidden Markov models; Humans; Multilayer perceptrons; Neural networks; Pattern classification; Pattern recognition; Power system modeling; Spatial databases;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/72.554190
Filename :
554190
Link To Document :
بازگشت