Skip to Main content Skip to Navigation
Conference papers

Maximally stable local description for scale selection

Gyuri Dorkó 1 Cordelia Schmid 1, *
* Corresponding author
1 LEAR - Learning and recognition in 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 : Scale and affine-invariant local features have shown excellent performance in image matching, object and texture recognition. This paper optimizes keypoint detection to achieve stable local descriptors, and therefore, an improved image representation. The technique performs scale selection based on a region descriptor, here SIFT, and chooses regions for which this descriptor is maximally stable. Maximal stability is obtained, when the difference between descriptors extracted for consecutive scales reaches a minimum. This scale selection technique is applied to multi-scale Harris and Laplacian points. Affine invariance is achieved by an integrated affine adaptation process based on the second moment matrix. An experimental evaluation compares our detectors to Harris-Laplace and the Laplacian in the context of image matching as well as of category and texture classification. The comparison shows the improved performance of our detector.
Document type :
Conference papers
Complete list of metadata

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/inria-00548588
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 9:49:36 AM
Last modification on : Monday, December 28, 2020 - 3:44:02 PM
Long-term archiving on: : Monday, March 21, 2011 - 3:21:58 AM

File

dorkoschmid_eccv06_MaxStableLo...
Files produced by the author(s)

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Gyuri Dorkó, Cordelia Schmid. Maximally stable local description for scale selection. European Conference on Computer Vision (ECCV '06), May 2006, Graz, Austria. pp.504--516, ⟨10.1007/11744085_39⟩. ⟨inria-00548588⟩

Share

Metrics

Record views

357

Files downloads

602