Oriented pooling for dense and non-dense rotation-invariant features - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

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

Wan-Lei Zhao
Hervé Jégou
  • Function : Author
  • PersonId : 833473
Guillaume Gravier

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.
Fichier principal
Vignette du fichier
paper_hal.pdf (2.9 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00841590 , version 1 (05-07-2013)
hal-00841590 , version 2 (23-08-2013)

Identifiers

  • HAL Id : hal-00841590 , version 2

Cite

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⟩
515 View
728 Download

Share

Gmail Facebook X LinkedIn More