Skip to Main content Skip to Navigation
New interface
Conference papers

Appariement d'images à des échelles différentes

Yves Dufournaud Cordelia Schmid 1 Radu Horaud 1 
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper presents a new method for image matching in the presence of large scale changes, which is invariant to image rotations and robust to perspective deformations. Matching is based on extracting interest points in images and on comparing these extracted parts based on local geyvalue invariants. It is derived how to adapt both interest point extraction and local invariant to scale changes. Extensive experimental results validate the feasibility of this approach and a multi-scale matching algorithm is proposed. Results for image pairs are extremely good for scale changes varying between 1 and 6.
Document type :
Conference papers
Complete list of metadata
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Tuesday, December 21, 2010 - 5:16:12 PM
Last modification on : Wednesday, May 4, 2022 - 12:12:03 PM
Long-term archiving on: : Tuesday, March 22, 2011 - 2:38:41 AM


Files produced by the author(s)


  • HAL Id : inria-00548298, version 1



Yves Dufournaud, Cordelia Schmid, Radu Horaud. Appariement d'images à des échelles différentes. Reconnaissance des Formes et Intelligence Artificielle (RFIA '00), Feb 2000, Paris, France. pp.327--336. ⟨inria-00548298⟩



Record views


Files downloads