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

Author

Chafik, Sanaa ; Daoudi, Imane ; El Ouardi, Hamid ; El Yacoubi, Mounim A. ; Dorizzi, Bernadette

Author_Institution

ENSEM, Hassan II Ain Chock Univ., Casablanca, Morocco

fYear

2014

fDate

28-30 May 2014

Firstpage

38

Lastpage

43

Abstract

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.

Keywords

content-based retrieval; image retrieval; indexing; visual databases; CPU; E2LSH; KRA+-Blocks; LSH family; approximation approach; content-based image retrieval; image descriptors; index structures; large-scale databases; locality sensitive hashing; million image descriptors; multidimensional indexing methods; sequential scan methods; Approximation methods; Indexing; Multimedia databases; Scalability; Vectors; Content based image retrieval (CBIR); Curse of dimensionality; Locality sensitive hashing; Multidimensional indexing; Scalability;

fLanguage

English

Publisher

ieee

Conference_Titel

Next Generation Networks and Services (NGNS), 2014 Fifth International Conference on

Conference_Location

Casablanca

Print_ISBN

978-1-4799-6608-0

Type

conf

DOI

10.1109/NGNS.2014.6990224

Filename

6990224