New features for complex Arabic fonts in cascading recognition system

Author

Slimane, Fouad ; Zayene, Oussama ; Kanoun, Slim ; Alimi, Adel M. ; Hennebert, Jean ; Ingold, Rolf

Author_Institution

Dept. of Inf., Univ. of Fribourg (unifr), Fribourg, Switzerland

fYear

2012

fDate

11-15 Nov. 2012

Firstpage

738

Lastpage

741

Abstract

We propose in this work an approach for automatic recognition of printed Arabic text in open vocabulary mode and ultra low resolution (72 dpi). This system is based on Hidden Markov Models using the HTK toolkit. The novelty of our work is in the analysis of three complex fonts presenting strong ligatures: DiwaniLetter, DecoTypeNaskh and DecoTypeThuluth. We propose a feature extraction based on statistical and structural primitives allowing a robust description of the different morphological variability of the considered fonts. The system is benchmarked on the Arabic Printed Text Image (APTI) database.

Keywords

feature extraction; hidden Markov models; image recognition; image resolution; natural language processing; statistical analysis; text detection; visual databases; vocabulary; APTI database; Arabic printed text image database; DecoTypeNaskh; DecoTypeThuluth; DiwaniLetter; HTK toolkit; automatic recognition; cascading recognition system; complex Arabic fonts; complex fonts; hidden Markov models; morphological variability; open vocabulary mode; printed Arabic text; robust description; statistical-based feature extraction; structural-based feature extraction; ultra low resolution; Character recognition; Databases; Educational institutions; Feature extraction; Hidden Markov models; Text recognition; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ICPR), 2012 21st International Conference on

Conference_Location

Tsukuba

ISSN

1051-4651

Print_ISBN

978-1-4673-2216-4

Type

conf

Filename

6460240