Matching of Graphical Symbols in Line-Drawing Images Using Angular Signature Information

Salvatore Tabbone 1 Laurent Wendling 1 Karl Tombre 1
1 QGAR - Querying Graphics through Analysis and Recognition
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : In this paper, a method for matching complex objects in line drawings is presented.Our approach is based on the notion of $\mathcal{F}$-signatures, which are a special kind of histograms of forces~\cite{matsakis98,matsakis99a,wendling02}. Such histograms have low time complexity and describe signatures which are invariant to fundamental geometrical transformations such as scaling, translation, symmetry and rotation. This article presents a new application of this notion, in the field of symbol identification and recognition. To improve the efficiency of matching, we propose to use an approximation of the $\mathcal{F}$-signature from Fourier series, and the associated matching.
Type de document :
Article dans une revue
International Journal on Document Analysis and Recognition, Springer Verlag, 2003, 6 (2), pp.115-125
Liste complète des métadonnées

https://hal.inria.fr/inria-00099540
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 09:38:25
Dernière modification le : jeudi 11 janvier 2018 - 06:19:59

Identifiants

  • HAL Id : inria-00099540, version 1

Collections

Citation

Salvatore Tabbone, Laurent Wendling, Karl Tombre. Matching of Graphical Symbols in Line-Drawing Images Using Angular Signature Information. International Journal on Document Analysis and Recognition, Springer Verlag, 2003, 6 (2), pp.115-125. 〈inria-00099540〉

Partager

Métriques

Consultations de la notice

157