de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Recognition with Local Features: the Kernel Recipe

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons84298

Wallraven,  C
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons83943

Graf,  ABA
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Wallraven, C., Caputo, B., & Graf, A. (2003). Recognition with Local Features: the Kernel Recipe. In Ninth IEEE International Conference on Computer Vision (ICCV 2003) (pp. 257-264). Los Alamitos, CA, USA: IEEE Computer Society.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-DB4D-F
Abstract
Recent developments in computer vision have shown that local features can provide efficient representations suitable for robust object recognition. Support Vector Machines have been established as powerful learning algorithms with good generalization capabilities. In this paper, we combine these two approaches and propose a general kernel method for recognition with local features. We show that the proposed kernel satisfies the Mercer condition and that this type of kernel is suitable for many standard local feature techniques in computer vision. Large-scale recognition results are presented on three different databases, which demonstrate that SVMs using the proposed kernel perform better than standard Nearest-Neighbor techniques on local features. In addition, experiments on noisy and occluded images show that local feature representations significantly outperform global approaches.