Accéder directement au contenu Accéder directement à la navigation
Article dans une revue

Using skeleton and Hough transform variant to correct skew in historical documents

Abstract : As a main part of several document analysis systems, Skew estimation represents one of the major research challenges, particularly in case of historical documents exploration. In this paper, we propose an original skew angle detection and correction technique. Morphological Skeleton is introduced to considerably diminish the amount of data by eliminating the redundant pixels and preserving only the central curves of the image components. Next, the proposed method uses Progressive Probabilistic Hough Transform (PPHT) to find image lines. At the end, a specific procedure is applied in order to measure the global skew angle of the document image from these identified lines. Experimental results demonstrate the accuracy and the effectiveness of our approach on skew angle detection upon three popular datasets covering many types of documents of diverse linguistic writings (Chinese, Greek and English) and different styles (horizontal or vertical orientations, including figures and tables, multi-columns page layouts).
Liste complète des métadonnées

Littérature citée [49 références]  Voir  Masquer  Télécharger

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-02447748
Contributeur : Dominique Michelucci <>
Soumis le : lundi 27 janvier 2020 - 17:45:36
Dernière modification le : vendredi 23 octobre 2020 - 16:47:07
Archivage à long terme le : : mardi 28 avril 2020 - 12:26:47

Fichier

Final-Version.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Omar Boudraa, Walid Khaled Hidouci, Dominique Michelucci. Using skeleton and Hough transform variant to correct skew in historical documents. Mathematics and Computers in Simulation, Elsevier, 2020, 167, pp.389-403. ⟨10.1016/j.matcom.2019.05.009⟩. ⟨hal-02447748⟩

Partager

Métriques

Consultations de la notice

274

Téléchargements de fichiers

793