Semi-local Affine Parts for Object Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2004

Semi-local Affine Parts for Object Recognition


This paper proposes a new approach for finding expressive and geometrically invariant parts for modeling 3D objects. The approach relies on identifying groups of local affine regions (image features having a characteristic appearance and elliptical shape) that remain approximately affinely rigid across a range of views of an object, and across multiple instances of the same object class. These groups, termed semi-local affine parts, are learned using correspondence search between pairs of unsegmented and cluttered input images, followed by validation against additional training images. The proposed approach is applied to the recognition of butterflies in natural imagery.
Fichier principal
Vignette du fichier
bmvc04.pdf (2.12 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00548542 , version 1 (20-12-2010)


  • HAL Id : inria-00548542 , version 1


Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. Semi-local Affine Parts for Object Recognition. British Machine Vision Conference (BMVC '04), Sep 2004, Kingston, United Kingdom. pp.779--788. ⟨inria-00548542⟩
613 View
2224 Download


Gmail Facebook Twitter LinkedIn More