Handwriting recognition system using fast wavelets transform

Author

Gumah, Mohamed E. ; Schneider, Etienne ; Aburas, Abdurazzag Ali

Author_Institution

Comput. & Inf. Sci. Dept., Univ. Teknol. PETRONAS, Tronoh, Malaysia

Volume

1

fYear

2010

fDate

15-17 June 2010

Firstpage

1

Lastpage

6

Abstract

Optical Characters Recognition (OCR) is one of the active subjects of research since the early days of computer science. There are two main stages in most of OCR systems: features extraction and classification. Artificial Neural Networks and Hidden Markov Models are the most popular classification methods used for OCR systems. In this paper, a method that relays on Fast Wavelets Transform (FWT) for optical character recognition is proposed. The idea of the proposed technique is to use the FWT to produce a coefficient vector of the character images, which will be directly used to recognize characters. Using the proposed technique, an accuracy of 94.18% in average was achieved.

Keywords

artificial intelligence; feature extraction; handwritten character recognition; hidden Markov models; image classification; neural nets; optical character recognition; wavelet transforms; OCR systems; artificial neural networks; character image coefficient vector; computer science; fast wavelet transform; feature extraction; handwriting recognition system; hidden Markov models; image classification; optical character recognition; Accuracy; Artificial neural networks; Character recognition; Hidden Markov models; Optical character recognition software; Wavelet transforms; Arabic characters; Fast wavelets transform; Optical Characters Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology (ITSim), 2010 International Symposium in

Conference_Location

Kuala Lumpur

ISSN

2155-897

Print_ISBN

978-1-4244-6715-0

Type

conf

DOI

10.1109/ITSIM.2010.5561302

Filename

5561302