A PGM-based System for Arabic Handwritten Word Recognition

Abstract : This paper describes a system for off-line recognition of handwritten Arabic words. It uses simple and easily extractable features to construct feature vectors for words in the vocabulary. Some of these features are statistical, based on pixel distributions and local pixel configurations. Others are structural, based on the presence of ascenders, descenders and diacritic points. The system is evolved based on vertical and horizontal Hidden Markov Models and Dynamic Bayesian Network. Our strategy consists of looking for various architectures and selecting those which provide the best recognition performance. Experiments on handwritten Arabic words from IFN/ENIT database and ancient manuscripts strongly support the feasibility of the proposed system. The recognition rates achieve 91.89% (IFN/ENIT) and 94.61% (ancient manuscripts).
Type de document :
Article dans une revue
Electronic Letters on Computer Vision and Image Analysis, ELCVIA, 2014, 13 (3), pp.22. 〈10.5565/rev/elcvia.575〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01254553
Contributeur : Abdel Belaid <>
Soumis le : mardi 12 janvier 2016 - 14:02:39
Dernière modification le : jeudi 11 janvier 2018 - 06:25:25

Lien texte intégral

Identifiants

Collections

Citation

Afef Kacem, Khémiri Akram, Belaïd Abdel. A PGM-based System for Arabic Handwritten Word Recognition. Electronic Letters on Computer Vision and Image Analysis, ELCVIA, 2014, 13 (3), pp.22. 〈10.5565/rev/elcvia.575〉. 〈hal-01254553〉

Partager

Métriques

Consultations de la notice

95