DocumentCode :
3398534
Title :
Object oriented modeling framework of a Kohonen network based character recognition system
Author :
Shukla, Ruchi ; Clarke, W.A. ; Marwala, T.
Author_Institution :
Dept. of Electr. & Electron. Eng. Sci., Univ. of Johannesburg, Johannesburg, South Africa
fYear :
2012
fDate :
10-12 Jan. 2012
Firstpage :
1
Lastpage :
7
Abstract :
This paper presents an object-oriented modeling framework of a Kohonen network based character recognition system. The Kohonen network provides faster feature extraction and classification, more so when there are multiple languages present. The object-oriented modeling framework is likely to assist in the development of a meta-model for multi-lingual character recognition.
Keywords :
character recognition; feature extraction; image classification; natural language processing; object-oriented methods; self-organising feature maps; Kohonen network; classification; faster feature extraction; meta-model development; multilingual character recognition system; object oriented modeling framework; Character recognition; Computers; Handwriting recognition; Hidden Markov models; Object oriented modeling; Training; Unified modeling language; handwriting recognition; kohonen network; object-oriented modeling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Communication and Informatics (ICCCI), 2012 International Conference on
Conference_Location :
Coimbatore
Print_ISBN :
978-1-4577-1580-8
Type :
conf
DOI :
10.1109/ICCCI.2012.6158810
Filename :
6158810
Link To Document :
بازگشت