Curvelets based queries for CBIR Application in handwriting collections - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

Curvelets based queries for CBIR Application in handwriting collections

Résumé

This paper presents a new use of the Curvelets Transform as a multiscale method for indexing linear singularities and curved handwritten shapes in documents images. As it belongs to the Wavelet family, this representation can be useful at several scales of details. The proposed scheme for handwritten shape characterization targets to detect oriented and curved fragments at different scales so as to compose an unique signature for each handwritten analyzed samples. In this way, Curvelets coefficients are used as a representation tool for handwriting when searching in large manuscripts databases by finding similar handwritten samples. Current results of ancient manuscripts retrieval are very promising with very satisfying precisions.
Fichier non déposé

Dates et versions

hal-01511334 , version 1 (20-04-2017)

Identifiants

  • HAL Id : hal-01511334 , version 1

Citer

Guillaume Joutel, Véronique Eglin, Stéphane Bres, Hubert Emptoz. Curvelets based queries for CBIR Application in handwriting collections. ICDAR, International conference on Document Analysis and Recognition, Sep 2007, Curitiba, Brazil. pp.649-653. ⟨hal-01511334⟩
163 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More