DMCA
Multi-Table Reinforcement Learning for Visual Object Recognition
by
Monica Piñol
,
Ricardo Toledo
,
M. Piñol
BibTeX
@MISC{Piñol_multi-tablereinforcement,
author = {Monica Piñol and Ricardo Toledo and M. Piñol},
title = {Multi-Table Reinforcement Learning for Visual Object Recognition},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract This paper presents a bag of feature based method for visual object recognition. Our contribution is focussed on the selection of the best feature descriptor. It is implemented by using a novel multi-table reinforcement learning method that selects among five of classical descriptors (i.e., Spin, SIFT, SURF, C-SIFT and PHOW) the one that best describes each image. Experimental results and comparisons are provided showing the improvements achieved with the proposed approach.
