Title :
Towards the on-line recognition of Arabic characters
Author :
Klassen, Tim J. ; Heywood, Malcolm I.
Author_Institution :
Fac. of Comput. Sci., Dalhousie Univ., Halifax, NS, Canada
fDate :
6/24/1905 12:00:00 AM
Abstract :
A generic system is proposed for the recognition of online handwritten Arabic characters. Automatic extraction of features from online data using self-organizing maps (SOMs) avoids heuristic extraction of features. The performance of a perceptron classifier is competitive with MLP (multilayer perceptron) and genetic programming-based approaches and is a better fit for hand-held computing devices
Keywords :
feature extraction; handwritten character recognition; image classification; online operation; optical character recognition; perceptrons; performance evaluation; self-organising feature maps; Arabic cursive handwriting; automatic feature extraction; genetic programming; hand-held computing devices; multilayer perceptron; online handwritten Arabic character recognition; perceptron classifier performance; self-organizing maps; Application software; Character recognition; Data mining; Feature extraction; Genetic programming; Handheld computers; Keyboards; Mobile computing; Shape; Speech recognition;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007809
