Hamming embedding and weak geometric consistency for large scale image search

DMCA

Hamming embedding and weak geometric consistency for large scale image search (2008)

Cached

Download Links

[lear.inrialpes.fr]
[hal.inria.fr]
[hal.inria.fr]

Other Repositories/Bibliography

DBLP

by Herve Jegou , Matthijs Douze , Cordelia Schmid

Venue:	In ECCV
Citations:	330 - 35 self

BibTeX

@INPROCEEDINGS{Jegou08hammingembedding,
    author = {Herve Jegou and Matthijs Douze and Cordelia Schmid},
    title = {Hamming embedding and weak geometric consistency for large scale image search},
    booktitle = {In ECCV},
    year = {2008}
}

OpenURL

Abstract

Abstract. This paper improves 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 suboptimality 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 the 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. 1

Keyphrases

large scale image search weak geometric consistency weak geometric consistency constraint binary signature large datasets significant improvement recent method short list bag-of-features image representation visual word precise representation full geometric transformation state-of-the-art method neighbor search inverted file re-ranking step wgc filter analyze bag-of-features

DMCA