Non-Mercer Kernels for SVM Object Recognition
Abstract
On one hand, Support Vector Machines have met with significant
success in solving difficult pattern recognition problems with
global features representation. On the other hand, local features in
images have shown to be suitable representations for efficient
object recognition. Therefore, it is natural to try to combine SVM
approach with local features representation to gain advantages on
both sides. We study in this paper the Mercer property of matching
kernels which mimic classical matching algorithms used in techniques
based on points of interest. We introduce a new statistical approach
of kernel positiveness. We show that despite the absence of an
analytical proof of the Mercer property, we can provide bounds on
the probability that the Gram matrix is actually positive definite
for kernels in large class of functions, under reasonable assumptions.
A few experiments validate those on object recognition tasks.
Reference
@inproceedings{jpt-bmvc04,
author = {Boughorbel, S. and Tarel, J.-P. and Fleuret, F.},
title = {Non-Mercer Kernels for SVM Object Recognition},
booktitle = {Proceedings of British Machine Vision Conference (BMVC'04)},
date = {September 7-9},
address = {London, England},
pages = {137 - 146},
year = {2004},
note = {http://perso.lcpc.fr/tarel.jean-philippe/publis/bmvc04.html}
}
Pdf file (351 Kb)
(c) BMVA