ARG based on arcs and segments to improve the symbol recognition by genetic algorithm

Jean-Pierre Salmon 1 Laurent Wendling 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 genetic matching scheme is extended to take into account primitive arcs and complex description in the pattern recognition process. Classical ways only focus on segments and are sensitive to over segmentation effect. Our approach allows to improve the recognition by handling more accurate description and also to decrease processing time by limiting the number of vertices to match. Experimental studies using real data attest the robustness of our approach.
Keywords : technical drawings graphic recognition vector representation inexact graph matching technical drawings.
Type de document :
Communication dans un congrès
Seventh International Workshop on Graphics Recognition - GREC'2007, Sep 2007, Curitiba, Brazil. 11 p., 2007, Session: 3 Symbol and shape description and recognition (2)
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/inria-00184880
Contributeur : Jean-Pierre Salmon <>
Soumis le : vendredi 2 novembre 2007 - 15:38:37
Dernière modification le : jeudi 11 janvier 2018 - 06:19:59
Document(s) archivé(s) le : lundi 12 avril 2010 - 01:13:38

Fichier

grec07.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00184880, version 1

Collections

INRIA | LORIA | UNIV-LORRAINE

Citation

Jean-Pierre Salmon, Laurent Wendling. ARG based on arcs and segments to improve the symbol recognition by genetic algorithm. Seventh International Workshop on Graphics Recognition - GREC'2007, Sep 2007, Curitiba, Brazil. 11 p., 2007, Session: 3 Symbol and shape description and recognition (2). 〈inria-00184880〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

196

Téléchargements de fichiers

87

Contact


archive-ouverte@inria.fr