Curvelets based queries for CBIR Application in handwriting collections

Guillaume Joutel 1 Véronique Eglin 1 Stéphane Bres 1 Hubert Emptoz 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01511334
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Thursday, April 20, 2017 - 5:25:15 PM
Last modification on : Friday, January 11, 2019 - 4:31:50 PM

Identifiers

  • HAL Id : hal-01511334, version 1

Citation

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⟩

Share

Metrics

Record views

221