Use of SLIC superpixels for ancient document image enhancement and segmentation

Abstract : Designing reliable and fast segmentation algorithms of ancient documents has been a topic of major interest for many libraries and the prime issue of research in the document analysis community. Thus, we propose in this article a fast ancient document enhancement and segmentation algorithm based on using Simple Linear Iterative Clustering (SLIC) superpixels and Gabor descriptors in a multi-scale approach. Firstly, in order to obtain enhanced backgrounds of noisy ancient documents, a novel foreground/background segmentation algo-rithm based on SLIC superpixels, is introduced. Once, the SLIC technique is carried out, the background and foreground superpixels are classified. Then, an enhanced and non-noisy background is achieved after processing the background superpixels. Subsequently, Gabor descriptors are only extracted from the selected foreground su-perpixels of the enhanced gray-level ancient book document images by adopting a multi-scale approach. Finally, for ancient document image segmentation, a foreground superpixel clustering task is performed by partitioning Gabor-based feature sets into compact and well-separated clusters in the feature space. The proposed algorithm does not assume any a priori information regarding document image content and structure and provides in-teresting results on a large corpus of ancient documents. Qualitative and numerical experiments are given to demonstrate the enhancement and segmentation quality.
Type de document :
Communication dans un congrès
Document Recoognition and Retrieval, Feb 2015, San Francisco, United States. 2015, 〈10.1117/12.2076020〉
Liste complète des métadonnées

Littérature citée [59 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01119158
Contributeur : Pierre Héroux <>
Soumis le : lundi 23 février 2015 - 10:35:43
Dernière modification le : mercredi 11 octobre 2017 - 11:18:05
Document(s) archivé(s) le : mardi 26 mai 2015 - 17:41:33

Fichier

DRR2015.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Maroua Mehri, Nabil Sliti, Pierre Héroux, Petra Gomez-Krämer, Najoua Essoukri Ben Amara, et al.. Use of SLIC superpixels for ancient document image enhancement and segmentation. Document Recoognition and Retrieval, Feb 2015, San Francisco, United States. 2015, 〈10.1117/12.2076020〉. 〈hal-01119158〉

Partager

Métriques

Consultations de
la notice

161

Téléchargements du document

198