DIMENSIONALITY REDUCTION OF VISUAL FEATURES USING SPARSE PROJECTORS FOR CONTENT-BASED IMAGE RETRIEVAL

Romain Negrel 1 David Picard 1 Philippe-Henri Gosselin 2, 1
1 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : In web-scale image retrieval, the most effective strategy is to ag-gregate local descriptors into a high dimensionality signature and then reduce it to a small dimensionality. Thanks to this strategy, web-scale image databases can be represented with small index and explored using fast visual similarities. However, the computation of this index has a very high complexity, because of the high di-mensionality of signature projectors. In this work, we propose a new efficient method to greatly reduce the signature dimensionality with low computational and storage costs. Our method is based on the linear projection of the signature onto a small subspace using a sparse projection matrix. We report several experimental results on two standard datasets (Inria Holidays and Oxford) and with 100k image distractors. We show that our method reduces both the projec-tors storage cost and the computational cost of projection step while incurring a very slight loss in mAP (mean Average Precision) per-formance of these computed signatures.
Document type :
Conference papers
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01081770
Contributor : Romain Negrel <>
Submitted on : Tuesday, November 11, 2014 - 9:53:17 AM
Last modification on : Friday, November 16, 2018 - 1:23:38 AM
Long-term archiving on : Thursday, February 12, 2015 - 10:05:26 AM

File

negrel-icip14.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01081770, version 1

Citation

Romain Negrel, David Picard, Philippe-Henri Gosselin. DIMENSIONALITY REDUCTION OF VISUAL FEATURES USING SPARSE PROJECTORS FOR CONTENT-BASED IMAGE RETRIEVAL. IEEE International Conference on Image Processing, Oct 2014, Paris, France. pp.2192-2196. ⟨hal-01081770⟩

Share

Metrics

Record views

608

Files downloads

249