A Fast Recognition System for Isolated Printed Characters Using Center of Gravity and Principal AxisReport as inadecuate




A Fast Recognition System for Isolated Printed Characters Using Center of Gravity and Principal Axis - Download this document for free, or read online. Document in PDF available to download.

The purpose of this paper is to propose a new multistage algorithm for the recognition of isolated characters. It was similar workdone before using only the center of gravity This paper isextended version of -A fast recognition system for isolated printed characters usingcenter of gravity-, LAP LAMBERT Academic Publishing 2011, ISBN: 978-38465-0002-6, but herewe add using principal axis in order to make the algorithm rotation invariant.In my previous work which is published in LAP LAMBERT, I face a big problemthat when the character is rotated I can’t recognize thecharacter. So this adds constrain on the document to be well oriented but here I use theprincipal axis in order to unify the orientation of the character set and thecharacters in the scanned document. The algorithm can be applied for anyisolated character such as Latin, Chinese, Japanese, and Arabic characters butit has been applied in this paper for Arabic characters. The approach usesnormalized and isolated characters of the same size and extracts an image signaturebased on the center of gravity of the character after making the characterprincipal axis vertical, and then the system compares these values to a set ofsignatures for typical characters of the set. The system then provides thecloseness of match to all other characters in the set.

KEYWORDS

OCR; Pattern Recognition; Confusion Matrix; Image Signature; Word Segmentation; Character Fragmentation

Cite this paper

A. Shaffie and G. Elkobrosy -A Fast Recognition System for Isolated Printed Characters Using Center of Gravity and Principal Axis,- Applied Mathematics, Vol. 4 No. 9, 2013, pp. 1313-1319. doi: 10.4236-am.2013.49177.





Author: Ahmed M. Shaffie, Galal A. Elkobrosy

Source: http://www.scirp.org/



DOWNLOAD PDF




Related documents