Title :
Recognition of Off-Line Handwritten Arabic Words Using Neural Network
Author :
Alma´adeed, Somaya
Author_Institution :
Dept. of Comput. Sci. & Eng., Qatar Univ., Doha
Abstract :
Neural network (NN) has been used with some success in recognizing printed Arabic words. In this paper, a complete scheme for unconstrained Arabic handwritten word recognition based on a neural network is proposed and discussed. The overall engine of this combination of a global feature scheme with a NN is a system able to classify Arabic-handwritten words of one hundred different writers. The system first attempts to remove some of the variation in the images that do not affect the identity of the handwritten word. Next, the system codes the skeleton and edge of the word so that feature information about the strokes in the skeleton is extracted. Then, a classification process based on the artificial NN classifier is used as global recognition engine, to classify the Arabic words. The output is a word in the dictionary. A detailed experiment is carried out, and successful recognition results are reported
Keywords :
feature extraction; handwritten character recognition; natural languages; neural nets; pattern classification; Arabic handwritten word recognition; feature extraction; global recognition engine; image classification; neural network; Computer science; Data mining; Feature extraction; Handwriting recognition; Image recognition; Image segmentation; Neural networks; Neurons; Solid modeling; Writing;
Conference_Titel :
Geometric Modeling and Imaging--New Trends, 2006
Conference_Location :
London, England
Print_ISBN :
0-7695-2604-7
DOI :
10.1109/GMAI.2006.43
