Skip to Main content Skip to Navigation
Conference papers

Un état de l'art des méthodes de localisation de symboles dans les documents graphiques

Thi Oanh Nguyen 1, 2 Salvatore Tabbone 2 
2 QGAR - Querying Graphics through Analysis and Recognition
LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : In this paper, we present a survey on symbol spotting methods for graphical documents. We classify these methods into two categories: structural and pixel-based approaches. Structural approaches are often based on graphs representations and frequently need a preliminary segmentation step in order to break documents into primitives. A symbol is then detected by regrouping neighbouring primitives under certain conditions. In pixel-based approaches, the symbol spotting is performed directly on the entire images without a preliminary segmentation step.
Complete list of metadata
Contributor : Thi Oanh Nguyen Connect in order to contact the contributor
Submitted on : Friday, April 9, 2010 - 5:26:12 PM
Last modification on : Friday, February 26, 2021 - 3:28:08 PM
Long-term archiving on: : Tuesday, September 14, 2010 - 5:51:14 PM


Files produced by the author(s)


  • HAL Id : inria-00472152, version 1



Thi Oanh Nguyen, Salvatore Tabbone. Un état de l'art des méthodes de localisation de symboles dans les documents graphiques. Colloque International Francophone sur l'Écrit et le Document - CIFED 2010, Mar 2010, Sousse, Tunisie. pp.217-232. ⟨inria-00472152⟩



Record views


Files downloads