Oriented pooling for dense and non-dense rotation-invariant features

Wan-Lei Zhao 1 Hervé Jégou 1 Guillaume Gravier 1
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This paper proposes a pooling strategy for local descriptors to produce a vector representation that is orientation-invariant yet implicitly incorporates the relative angles between features measured by their dominant orientation. This pooling is associated with a similarity metric that ensures that all the features have undergone a comparable rotation. This approach is especially effective when combined with dense oriented features, in contrast to existing methods that either rely on oriented features extracted on key points or on non-oriented dense features. The interest of our approach in a retrieval scenario is demonstrated on popular benchmarks comprising up to 1 million database images.
Document type :
Conference papers
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-00841590
Contributor : Hervé Jégou <>
Submitted on : Friday, August 23, 2013 - 12:06:38 PM
Last modification on : Friday, November 16, 2018 - 1:25:57 AM
Long-term archiving on : Thursday, April 6, 2017 - 6:01:34 AM

File

paper_hal.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00841590, version 2

Citation

Wan-Lei Zhao, Hervé Jégou, Guillaume Gravier. Oriented pooling for dense and non-dense rotation-invariant features. BMVC - 24th British Machine Vision Conference, Sep 2013, Bristol, United Kingdom. ⟨hal-00841590v2⟩

Share

Metrics

Record views

1470

Files downloads

416