Fast Identification of Visual Documents Using Local Descriptors - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Fast Identification of Visual Documents Using Local Descriptors

Résumé

In this paper we introduce a system for the identification of visual documents. Since it stems from content-based document indexing and retrieval, our system does not need to rely on textual annotations, watermarks or other metadata, which can be missing or incorrect. Our retrieval system is based on local descriptors, which have been shown to provide accurate and robust description. Because of the high computational costs associated to the matching of local descriptors, we propose Projection KD-Forest: an indexing technique which allows efficient approximate k nearest neighbors search. Experiments demonstrate that the Projection KD-Forest allows the system to provide prompt results with negligible loss on accuracy. The Projection KD-Forest also compares well when contrasted to other strategies of k nearest neighbors search.
Fichier non déposé

Dates et versions

hal-01301558 , version 1 (12-04-2016)

Identifiants

Citer

Eduardo Valle, Matthieu Cord, Sylvie Philipp-Foliguet. Fast Identification of Visual Documents Using Local Descriptors. ACM Symposium on Document Engineering, DocEng, Sep 2008, Sao Paulo, Brazil. pp.173-176, ⟨10.1145/1410140.1410175⟩. ⟨hal-01301558⟩
82 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More