16 December 1988 Recognition Of Hand Written Arabic Characters
Author Affiliations +
Abstract
This paper introduces a novel statistical approach for recognizing handwritten Arabic characters. The proposed method involves, as a first step, digitization of the segmented character. The secondary characters are then isolated and identified separately thereby reducing the recognition issue to a 20 class problem. The moments of the horizontal and vertical projections of the remaining primary characters are estimated and normalized with respect to the zero order moment. Simple measures of shape are obtained from the normalized moments and incorporated into a feature vector. Classification is accomplished using quadratic discriminant functions. Results confirming that the method show considerable merit are presented.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
H. Al -Yousefi, H. Al -Yousefi, S. S. Udpa, S. S. Udpa, } "Recognition Of Hand Written Arabic Characters", Proc. SPIE 0974, Applications of Digital Image Processing XI, (16 December 1988); doi: 10.1117/12.948475; https://doi.org/10.1117/12.948475
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Data acquisition from cemetery headstones
Proceedings of SPIE (February 03 2013)
Locally adaptive document skew detection
Proceedings of SPIE (April 02 1997)
Offline recognition of handwritten cursive words
Proceedings of SPIE (July 31 1992)
Document image database indexing with pictorial dictionary
Proceedings of SPIE (February 26 2010)
Automatic document reading system for technical drawings
Proceedings of SPIE (December 17 2001)
Low-cost asset tracking using location-aware camera phones
Proceedings of SPIE (September 07 2010)

Back to Top