Recent advance in image search

Hervé Jégou 1, 2 Matthijs Douze 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 VISTAS - Spatio-Temporal Vision and Learning
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper introduces recent methods for large scale image search. State-of-the-art methods build on the bag-of-features image representation. We first analyze bag-of-features in the framework of approximate nearest neighbor search. This shows the sub-optimality of such a representation for matching descriptors and leads us to derive a more precise representation based on 1) Hamming embedding (HE) and 2) weak geometric consistency constraints (WGC). HE provides binary signatures that refine the matching based on visual words. WGC filters matching descriptors that are not consistent in terms of angle and scale. HE and WGC are integrated within an inverted file and are efficiently exploited for all images, even in the case of very large datasets. Experiments performed on a dataset of one million of images show a significant improvement due to the binary signature and the weak geometric consistency constraints, as well as their efficiency. Estimation of the full geometric transformation, i.e., a re-ranking step on a short list of images, is complementary to our weak geometric consistency constraints and allows to further improve the accuracy.
Document type :
Book sections
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

wgc.jpg
wgc.jpg
https://hal.inria.fr/inria-00548648
Contributor : Hervé Jégou <>
Submitted on : Monday, December 20, 2010 - 10:24:11 AM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Long-term archiving on: Monday, March 21, 2011 - 3:27:27 AM

Files

ETCV08.pdf
Files produced by the author(s)

Identifiers

Collections

CNRS | INRIA | IRISA | UNIV-RENNES1 | UGA | LJK_GI_LEAR | LJK_GI | LJK | UR1-UFR-ISTIC | UNIV-RENNES | INSA-GROUPE

Citation

Hervé Jégou, Matthijs Douze, Cordelia Schmid. Recent advance in image search. Frank Nielsen. Emerging Trends in Visual Computing, 5416, Springer-Verlag, pp.305-326, 2009, Lecture Notes in Computer Science, 978-3-642-00826-9. ⟨10.1007/978-3-642-00826-9_14⟩. ⟨inria-00548648⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

1061

Files downloads

716

 

 

Contact

archive-ouverte@inria.fr