Online Arabic Handwriting Modeling System Based on the Graphemes Segmentation

Author

Boubaker, Houcine ; El Baati, Abdelkarim ; Kherallah, Monji ; Alimi, Adel M. ; Elabed, Haikel

Author_Institution

REGIM: Res. Group on Intell. Machines, Univ. of Sfax, Sfax, Tunisia

fYear

2010

fDate

23-26 Aug. 2010

Firstpage

2061

Lastpage

2064

Abstract

We present in this paper a new approach of online Arabic handwriting modeling based on the graphemes segmentation. This segmentation rests on the previous detection of baseline. It involves the detection of two types of topologically meaningful points: the backs of the valleys adjoining the baseline and the angular points. The stage of features extraction allows to model the shapes of segmented graphemes by relevant geometric parameters and to estimate their diacritics fuzzy affectation rates. The test results show a significant improvement in recognition rate with the introduction of new pertinent parameters.

Keywords

feature extraction; fuzzy set theory; geometry; handwriting recognition; handwritten character recognition; image segmentation; natural language processing; object detection; shape recognition; angular point; baseline detection; diacritics fuzzy affectation rate; feature extraction; geometric parameter; graphemes segmentation; online Arabic handwriting modeling system; point detection; shape modeling; Feature extraction; Handwriting recognition; Hidden Markov models; Manganese; Shape; Text analysis; Trajectory; baseline detection; grapheme segmentation; handwriting modeling; online handwriting;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ICPR), 2010 20th International Conference on

Conference_Location

Istanbul

ISSN

1051-4651

Print_ISBN

978-1-4244-7542-1

Type

conf

DOI

10.1109/ICPR.2010.507

Filename

5597276