Share Email Print

Proceedings Paper

Use of SLIC superpixels for ancient document image enhancement and segmentation
Author(s): Maroua Mehri; Nabil Sliti; Pierre Héroux; Petra Gomez-Krämer; Najoua Essoukri Ben Amara; Rémy Mullot
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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 algorithm 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 superpixels 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 interesting results on a large corpus of ancient documents. Qualitative and numerical experiments are given to demonstrate the enhancement and segmentation quality.

Paper Details

Date Published: 8 February 2015
PDF: 12 pages
Proc. SPIE 9402, Document Recognition and Retrieval XXII, 940205 (8 February 2015); doi: 10.1117/12.2076020
Show Author Affiliations
Maroua Mehri, Univ. de La Rochelle (France)
Univ. de Rouen (France)
Nabil Sliti, Univ. de Sousse (Tunisia)
Pierre Héroux, Univ. de Rouen (France)
Petra Gomez-Krämer, Univ. de La Rochelle (France)
Najoua Essoukri Ben Amara, Univ. de Sousse (Tunisia)
Rémy Mullot, Univ. de La Rochelle (France)

Published in SPIE Proceedings Vol. 9402:
Document Recognition and Retrieval XXII
Eric K. Ringger; Bart Lamiroy, Editor(s)

© SPIE. Terms of Use
Back to Top