Object categorization with SVM: kernels for local features
Jan Eichhorn and Olivier Chapelle
Max Planck Institute for Biological Cybernetics, Germany.
In this paper, we propose to combine an efficient image representation based on local descriptors with a Support Vector Machine classifier in order to perform object categorization. For this purpose, we apply kernels defined on sets of vectors. After testing different combinations of kernel / local descriptors, we have been able to identify a very performant one.
|EPrint Type:||Monograph (Working Paper)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Jan Eichhorn|
|Deposited On:||19 December 2004|