A new algorithm for machine printed Arabic character segmentation

by: Liying Zheng, Abbas H Hassin, Xianglong Tang

Pattern Recognition Letters, Vol. 25, No. 15. (November 2004), pp. 1723-1729.

View FullText article

DOI, ScienceDirect

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

vmoa

Find related articles with these CiteULike tags

arabic, character, segmentation

Abstract

The major problem with machine printed Arabic character segmentation is the shape of the letter depending on its location in the word. In this paper, a new machine printed Arabic character segmentation algorithm, which is based on the vertical histogram and some rules, is presented. The rules which are based on, not only the structural characteristics between background regions and character components but also the characteristics of isolated Arabic characters, are used to check whether the sub-word includes only one character. Then we use the vertical histogram and some other rules to find real segmentation points. Finally, we split the sub-word at the segmentation points. The experimental results show that the algorithm achieved about 94% correct segmentation.

@article{citeulike:820304, abstract = {The major problem with machine printed Arabic character segmentation is the shape of the letter depending on its location in the word. In this paper, a new machine printed Arabic character segmentation algorithm, which is based on the vertical histogram and some rules, is presented. The rules which are based on, not only the structural characteristics between background regions and character components but also the characteristics of isolated Arabic characters, are used to check whether the sub-word includes only one character. Then we use the vertical histogram and some other rules to find real segmentation points. Finally, we split the sub-word at the segmentation points. The experimental results show that the algorithm achieved about 94\% correct segmentation.}, author = {Zheng, Liying and Hassin, Abbas H. and Tang, Xianglong }, citeulike-article-id = {820304}, doi = {10.1016/j.patrec.2004.06.015}, journal = {Pattern Recognition Letters}, keywords = {arabic, character, segmentation}, month = {November}, number = {15}, pages = {1723--1729}, posted-at = {2006-08-29 02:33:17}, priority = {3}, title = {A new algorithm for machine printed Arabic character segmentation}, url = {http://dx.doi.org/10.1016/j.patrec.2004.06.015}, volume = {25}, year = {2004} }

RIS record

TY - JOUR ID - citeulike:820304 L3 - citeulike-article-id:820304 TI - A new algorithm for machine printed Arabic character segmentation JF - Pattern Recognition Letters VL - 25 IS - 15 SP - 1723 EP - 1729 N2 - The major problem with machine printed Arabic character segmentation is the shape of the letter depending on its location in the word. In this paper, a new machine printed Arabic character segmentation algorithm, which is based on the vertical histogram and some rules, is presented. The rules which are based on, not only the structural characteristics between background regions and character components but also the characteristics of isolated Arabic characters, are used to check whether the sub-word includes only one character. Then we use the vertical histogram and some other rules to find real segmentation points. Finally, we split the sub-word at the segmentation points. The experimental results show that the algorithm achieved about 94% correct segmentation. KW - arabic KW - character KW - segmentation AU - Zheng, Liying AU - Hassin, Abbas AU - Tang, Xianglong PY - 2004/11// UR - http://dx.doi.org/10.1016/j.patrec.2004.06.015 ER -

RIS BibTeX