Contextual Detection of Drawn Symbols in Old Maps

Abstract : In this paper, we tackle the problem of detecting drawn symbols in old maps. We propose a novel approach that combines powerful low level descriptors to represent the local content of the objects, and contextual features to overcome the local analysis ambiguity. Our contribution is two-fold. Firstly, we propose a novel contextual feature adapted to our problem, where the context is integrated at two levels. In a close neighborhood, a local analysis is carried out to remove visual ambiguities between symbols. In a larger extent, co-occurrence statistics between classes are stored. Secondly, we propose an entire processing chain for learning and detection. The proposed method is evaluated on real french maps from the 18th century. The experiments show the efficiency of the detection system, and validate the relevance of the proposed contextual feature to improve detection performances.
Type de document :
Communication dans un congrès
International Conference on Image Processing (ICIP), Sep 2012, Orlando, Florida, United States. IEEE, International Conference on Image Processing (ICIP), pp.837-840, 〈10.1109/ICIP.2012.6466990〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01270081
Contributeur : Lip6 Publications <>
Soumis le : vendredi 5 février 2016 - 16:04:36
Dernière modification le : vendredi 31 août 2018 - 09:25:56

Identifiants

Collections

Citation

Jonathan Guyomard, Nicolas Thome, Matthieu Cord, Thierry Artières. Contextual Detection of Drawn Symbols in Old Maps. International Conference on Image Processing (ICIP), Sep 2012, Orlando, Florida, United States. IEEE, International Conference on Image Processing (ICIP), pp.837-840, 〈10.1109/ICIP.2012.6466990〉. 〈hal-01270081〉

Partager

Métriques

Consultations de la notice

94