Structural Features Extraction for Handwritten Arabic Personal Names Recognition

Abstract : Due to the nature of handwriting with high degree of variability and imprecision, obtaining features that represent words is a difficult task. In this research, a features extraction method for handwritten Arabic word recognition is investigated. Its major goal is to maximize the recognition rate with the least amount of elements. This method incorporates many characteristics of handwritten characters based on structural information (loops, stems, legs, diacritics). Experiments are performed on Arabic personal names extracted from registers of the national Tunisian archive and on some Tunisian city names of IFN-ENIT database. The obtained results presented are encouraging and open other perspectives in the domain of the features and classifiers selection of Arabic Handwritten word recognition.
Type de document :
Communication dans un congrès
ICFHR - 13th International Conference on Frontiers in Handwriting Recognition - 2012, Sep 2012, Bari, Italy. IEEE, pp.268-273, 2012, 〈10.1109/ICFHR.2012.276〉
Liste complète des métadonnées

Littérature citée [6 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00779260
Contributeur : Abdel Belaid <>
Soumis le : mardi 29 janvier 2013 - 16:32:54
Dernière modification le : mardi 24 avril 2018 - 13:34:09
Document(s) archivé(s) le : mardi 30 avril 2013 - 02:35:08

Fichier

version_publiee_ICFHRpaper043....
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Afef Kacem, Nadia Aouïti, Abdel Belaïd. Structural Features Extraction for Handwritten Arabic Personal Names Recognition. ICFHR - 13th International Conference on Frontiers in Handwriting Recognition - 2012, Sep 2012, Bari, Italy. IEEE, pp.268-273, 2012, 〈10.1109/ICFHR.2012.276〉. 〈hal-00779260〉

Partager

Métriques

Consultations de la notice

228

Téléchargements de fichiers

739