TY  - CONF
CY  - Kuala Lumpur
AV  - none
N2  - 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. © 2010 IEEE.
N1  - cited By 2; Conference of 2010 International Symposium on Information Technology, ITSim'10 ; Conference Date: 15 June 2010 Through 17 June 2010; Conference Code:81915
TI  - Handwriting recognition system using Fast Wavelets Transform
ID  - scholars1065
KW  - A-coefficient; Arabic characters; Artificial Neural Network; Character images; Classification methods; Features extraction; Handwriting recognition; Optical Characters Recognition; Wavelets transform
KW  -  Feature extraction; Hidden Markov models; Information technology; Neural networks; Optical character recognition
KW  -  Wavelet transforms
Y1  - 2010///
SN  - 9781424467181
A1  - Gumah, M.E.
A1  - Schneider, E.
A1  - Aburas, A.A.
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-78049396533&doi=10.1109%2fITSIM.2010.5561302&partnerID=40&md5=a839702dfcd624bb464ccad31f3a9546
VL  - 1
ER  -