Back to Search Start Over

Locality sensitive hashing for content based image retrieval: A comparative experimental study

Authors :
Sanaa Chafik
Mounim A. El Yacoubi
Hamid El Ouardi
Imane Daoudi
Bernadette Dorizzi
Faculté des Sciences Aïn Chock [Casablanca] (FSAC)
Université Hassan II [Casablanca] (UH2MC)
Département Electronique et Physique (EPH)
Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)
Traitement de l'Information Pour Images et Communications (TIPIC-SAMOVAR)
Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (SAMOVAR)
Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)-Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)
Centre National de la Recherche Scientifique (CNRS)
Source :
Proceedings NGNS 2014 : 5th International Conference on Next Generation Networks and Services, NGNS 2014 : 5th International Conference on Next Generation Networks and Services, NGNS 2014 : 5th International Conference on Next Generation Networks and Services, May 2014, Casablanca, Morocco. pp.38-43, ⟨10.1109/NGNS.2014.6990224⟩
Publication Year :
2014
Publisher :
IEEE, 2014.

Abstract

International audience; This paper presents a comparative experimental study of the multidimensional indexing methods based on the approximation approach. We are particularly interested in the LSH family, which provides efficient index structures and solves the dimensionality curse problem. The goal is to understand the performance gain and the behavior of this family of methods on large-scale databases. E2LSH is compared to the KRA+-Blocks and the sequential scan methods. Two criteria are used in evaluating the E2LSH performances, namely average precision and CPU time using a database of one million image descriptors

Details

Database :
OpenAIRE
Journal :
2014 International Conference on Next Generation Networks and Services (NGNS)
Accession number :
edsair.doi.dedup.....6f8746ccf998e89d8624a58da908270a
Full Text :
https://doi.org/10.1109/ngns.2014.6990224