Abstract
A typewritten Arabic OCR (Optical Character Recognition system) is introduced. The system automatically predicts the size of the font, and uses it in separating lines, words and subwords. Then, it scans the text in a way similar to what the Arabic readers do to recognize and segment the different characters. A set of nine Neural Network modules is used for this process guided by a novel algorithm. The whole text is, then, rebuilt using the recognized characters and some error correction loops are applied. Using Neural Network classifiers allows an efficient hardware implementation and good “generalization” abilities.
Similar content being viewed by others
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Raafat, H., Auda, G. (1995). An arabic OCR using neural network classifiers. In: Chin, R.T., Ip, H.H.S., Naiman, A.C., Pong, TC. (eds) Image Analysis Applications and Computer Graphics. ICSC 1995. Lecture Notes in Computer Science, vol 1024. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60697-1_149
Download citation
DOI: https://doi.org/10.1007/3-540-60697-1_149
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60697-0
Online ISBN: 978-3-540-49298-6
eBook Packages: Springer Book Archive