One-shot field spotting on colored forms using subgraph isomorphism

Abstract : This paper presents an approach for spotting tex-tual fields in commercial and administrative colored forms. We proceed by locating these fields thanks to their neighboring context which is modeled with a structural representation. First, informative zones are extracted. Second, forms are represented by graphs. In these graphs, nodes represent colored rectangular shapes while edges represent neighboring relations. Finally, the neighboring context of the queried region of interest is modeled as a graph. Subgraph isomorphism is applied in order to locate this ROI in the structural representation of a whole document. Evaluated on a 130-document image dataset, experimental results show up that our approach is efficient and that the requested information is found even if its position is changed.
Type de document :
Communication dans un congrès
International Conference on Document Analysis and Recognition, 2015, Nancy, France. pp.586-590, 2015, 〈10.1109/ICDAR.2015.7333829〉
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01249470
Contributeur : Pierre Héroux <>
Soumis le : vendredi 1 janvier 2016 - 19:07:27
Dernière modification le : samedi 16 décembre 2017 - 00:13:09
Document(s) archivé(s) le : jeudi 7 avril 2016 - 17:04:03

Fichier

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

Identifiants

Collections

Citation

Maroua Hammami, Pierre Héroux, Sébastien Adam, Vincent Poulain d'Andecy. One-shot field spotting on colored forms using subgraph isomorphism. International Conference on Document Analysis and Recognition, 2015, Nancy, France. pp.586-590, 2015, 〈10.1109/ICDAR.2015.7333829〉. 〈hal-01249470〉

Partager

Métriques

Consultations de la notice

78

Téléchargements de fichiers

37