department of informatics

PAWR: Printed Multi-Font and Multi-Size Arabic Word Recognition at Ultra-Low Resolution

Printed Multi-Font and Multi-Size Arabic Word Recognition at Ultra-Low Resolution

The objective of this thesis is to develop a multi-font and multi-size recognition system for Arabic text images at ultra-low resolution and to extend it easily to the recognition of Arabic handwritten or scanned documents. This system is based on hidden Markov models and Gaussian Mixture models. The goal is also to bring together a wide vocabulary to develop a recognition system for open vocabulary that can recognize any Arabic words. 

The system is benchmarked on the Arabic Printed Text Image (APTI) database.

Participants:

Partners: The project is performed in collaboration with

  • University of Fribourg (Switzerland)
  • University of Sfax(Tunisia)

APTI Database : Arabic Printed Text Image Database home page


Publications related to this project

2012

  • Fouad Slimane, Slim Kanoun, Jean Hennebert, Adel M. Alimi, Rolf Ingold, "A Study on Font-Family and Font-Size Recognition Applied to Arabic Word Images at Ultra-Low Resolution".Pattern  recognition Letters (PRL), to be published.
  • Fouad Slimane, Oussema Zayene, Slim Kanoun, Adel M. Alimi, Jean Hennebert, Rolf Ingold, "A New Multi-font ArabicWord Recognition System for Complex Fonts".  In proc. of 21th International Conference on Pattern Recognition (ICPR 2012), Tsukuba (Japan), November 11-15, 2012, to be published.
  • Fouad Slimane, Slim Kanoun, Jean Hennebert, Rolf Ingold, Adel M. Alimi, "Benchmarking Strategy for Arabic Screen Rendered Word Recognition".  In Guide to OCR for Arabic Scripts, Volker Margner and Haikal El-Abed, Springer London, 2012, pp. 423-450.
  • Oussema Zayene, Fouad Slimane, "Reconnaissance de l'écriture arabe imprimée multi-fontes à très basse résolution." Journée Jeunes Chercheurs CORIA-CIFED,  Bordeaux  (France),  March 21 - 23 2012 , pp. 443-448.
  •  Fouad Slimane, Slim Kanoun, Jean Hennebert, Rolf Ingold, Adel M. Alimi, "A New Baseline Estimation Method Applied to Arabic Word Recognition".  10th IAPR International Workshop on Document Analysis Systems (DAS 2012), Gold Cost, Queensland (Australia), March 27-29 2012, to be published.

2011

  • Houda Gaddour,  Hanène Guesmi,  Fouad Slimane,  Slim Kanoun,  Jean Hennebert,  "A New Method for Ranking of Word Hypotheses generated from OCR: The Application on the Arabic Word Recognition" In proc. of The Twelfth IAPR Conference on Machine Vision Applications  (MVA 2011),  Nara  (Japan),  June  13 - 15  2011 , pp. 311-315.
  • Fouad Slimane, Slim Kanoun, Haikel El-Abed, Adel M. Alimi, Rolf Ingold, Jean Hennebert, "Arabic Recognition Competition: Multi-font Multi-size Digitally Represented Text".  In proc. of The Eleventh International Conference on Document Analysis and Recognition (ICDAR 2011), Beijing (China), September 18-21, 2011, pp. 1449-1453.

2010

  • Fouad Slimane,  Slim Kanoun,  Adel M. Alimi,  Jean Hennebert,  Rolf Ingold,  "Comparison of Global and Cascading Recognition Systems Applied to Multi-font Arabic Text." In proc. of 10th ACM Symposium on Document Engineering  (DocEng2010),  Manchester  (United Kingdom),  September  21 - 24  2010 , pp. 161-164. DOI=10.1145/1860559.1860591
  • Fouad Slimane,  Rolf Ingold,  Slim Kanoun,  Adel M. Alimi,  Jean Hennebert,  "Impact of Character Models Choice on Arabic Text Recognition Performance." In proc. of 12th International Conference on Frontiers in Handwriting Recognition  (ICFHR 2010),  Kolkata  (India),  November  16 - 18  2010 , pp. 670-675.
  • Fouad Slimane,  Slim Kanoun,  Adel M. Alimi,  Rolf Ingold,  Jean Hennebert,  "Gaussian Mixture Models for Arabic Font Recognition." In proc. of 20th International Conference on Pattern Recognition  (ICPR 2010),  Istanbul  (Turkey),  August  23 - 26  2010 , pp. 2174-2177.

2009

  • Fouad Slimane,  Slim Kanoun,  Jean Hennebert,  Adel M. Alimi,  Rolf Ingold,  "Modèles de Markov Cachés et Modèle de Longueur pour la Reconnaissance de l’Ecriture Arabe à Basse Résolution." In proc. of MAnifestation des JEunes Chercheurs en Sciences et Technologies de l'Information et de la Communication  (MajecSTIC 2009),  Avignon  (France),  November  16 - 18  2009
  • Slim Kanoun,  Fouad Slimane,  Hanène Guesmi,  Rolf Ingold,  Adel M. Alimi,  Jean Hennebert,  "Affixal Approach versus Analytical Approach for Off-Line Arabic Decomposable Vocabulary Recognition." In proc. of 10th IEEE International Conference on Document Analysis and Recognition  (ICDAR 2009),  Barcelona  (Spain),  July  26 - 29  2009 , pp. 661-665.
  • Fouad Slimane,  Rolf Ingold,  Slim Kanoun,  Adel M. Alimi,  Jean Hennebert,  "A New Arabic Printed Text Image Database and Evaluation Protocols." In proc. of 10th IEEE International Conference on Document Analysis and Recognition  (ICDAR 2009),  Barcelona  (Spain),  July  26 - 29  2009 , pp. 946-950.
  • F. Slimane, R. Ingold, S. Kanoun, M. A. Alimi and J. Hennebert, "Database and Evaluation Protocols for Arabic Printed Text Recognition", Internal research report, DIUF, University of Fribourg, Switzerland, 2009.

2008

  • Fouad Slimane,  Rolf Ingold,  Adel M. Alimi,  Jean Hennebert,  "Duration Models for Arabic Text Recognition using Hidden Markov Models." In proc. of IEEE International Conference on Computational Intelligence for Modelling, Control and Automation  (CIMCA 08),  Vienna  ( Austria),  December  10 - 12  2008 , pp. 838-843.