Matching by local invariants

Cordelia Schmid 1 Roger Mohr 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper presents a matching method which is based on invariants of the luminance function. This makes matching possible in the case of important geometric transformations between images. The method is robust to occlusion, as local properties of the image signal are used. We propose to use differential measures invariant to rotations in a multi-scale framework. Promising results are obtained which might be used for a variety of applications.
Document type :
Reports
Complete list of metadatas

https://hal.inria.fr/inria-00074046
Contributor : Rapport de Recherche Inria <>
Submitted on : Wednesday, May 24, 2006 - 2:23:01 PM
Last modification on : Wednesday, April 11, 2018 - 1:54:18 AM
Long-term archiving on: Sunday, April 4, 2010 - 9:23:18 PM

Identifiers

  • HAL Id : inria-00074046, version 1

Collections

Citation

Cordelia Schmid, Roger Mohr. Matching by local invariants. [Research Report] RR-2644, INRIA. 1995. ⟨inria-00074046⟩

Share

Metrics

Record views

277

Files downloads

946