Experiments with Kohonen´s learning vector quantization in handwritten character recognition systems

Author

Jameel, Akhtar ; Koutsougeras, Cris

Author_Institution

Dept. of Comput. Sci., Tulane Univ., New Orleans, LA, USA

Volume

1

fYear

1994

fDate

3-5 Aug 1994

Firstpage

595

Abstract

In this paper we present the results of classification of handwritten characters on a Kohonen neural network. Three types of features, Fourier transform, geometric moments and shadow feature extracted from handwritten character data were used for classification. Classification accuracy is found to be much higher with the shadow feature in comparison to the more traditional Fourier transform and geometric moments. We have also explored the relation between Kohonen´s learning of orientation based correlations and the learning rule of a minimum distance approach, used in a feedforward Athena neural network

Keywords

Fourier transforms; character recognition; feature extraction; feedforward neural nets; learning (artificial intelligence); pattern classification; self-organising feature maps; vector quantisation; Fourier transform; Kohonen neural network; classification accuracy; feedforward Athena neural network; geometric moments; handwritten character data; handwritten character recognition systems; learning rule; learning vector quantization; minimum distance approach; orientation based correlations; shadow feature; Automation; Character recognition; Computer science; Data mining; Feature extraction; Feedforward neural networks; Fourier transforms; Neural networks; Testing; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1994., Proceedings of the 37th Midwest Symposium on

Conference_Location

Lafayette, LA

Print_ISBN

0-7803-2428-5

Type

conf

DOI

10.1109/MWSCAS.1994.519365

Filename

519365