A feature-based neural wavelet optical character recognition system

Author

Iftekharuddin, K.M. ; Jemili, K. ; Karim, M.A.

Author_Institution

BDM Federal, Kettering, UK

Volume

2

fYear

1995

fDate

22-26 May 1995

Firstpage

621

Abstract

A hybrid character recognition system is studied using feature extraction method. The features are extracted using wavelet transform, pre-classified using a k-nearest neighbor-based neural net and subsequently post-processed using an optical correlator

Keywords

data compression; feature extraction; image classification; image coding; image matching; matched filters; multilayer perceptrons; neural net architecture; optical character recognition; optical correlation; optical neural nets; spatial filters; spatial light modulators; wavelet transforms; adaptive classifier; amplitude-modulated phase-only filter; feature extraction method; hybrid character recognition system; image compression; k-nearest neighbor-based neural net; matched filter; multilayer optical processor; neural wavelet architecture; optical character recognition system; optical correlator postprocessor; parallel operation capability; wavelet decomposition; wavelet preprocessor; wavelet transform; Character recognition; Feature extraction; Holographic optical components; Holography; Matched filters; Neural networks; Optical character recognition software; Optical filters; Pattern recognition; Spatial databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace and Electronics Conference, 1995. NAECON 1995., Proceedings of the IEEE 1995 National

Conference_Location

Dayton, OH

ISSN

0547-3578

Print_ISBN

0-7803-2666-0

Type

conf

DOI

10.1109/NAECON.1995.522002

Filename

522002