Title :
Off-line Arabic character recognition
Author :
Goraine, Habib ; Usher, Mike ; Al-Emami, S.
Author_Institution :
Dept. of Cybern., Reading Univ., UK
fDate :
7/1/1992 12:00:00 AM
Abstract :
A personal computer-based Arabic character recognition system that performs three preprocessing stages sequentially, thinning, stroke segmentation, and sampling, is described. The eight-direction code used for stroke representation and classification, the character classification done at primary and secondary levels, and the contextual postprocessor used for error detection and correction are described. Experimental results obtained using samples of handwritten and typewritten Arabic words are presented.<>
Keywords :
character recognition; computerised pattern recognition; error correction; error detection; microcomputer applications; character classification; contextual postprocessor; eight-direction code; error correction; error detection; handwritten; off-line Arabic character recognition; sampling; stroke segmentation; thinning; typewritten; Cameras; Character recognition; Cybernetics; Data compression; Handwriting recognition; Image processing; Image sampling; Image segmentation; Pattern recognition; Shape;
