An efficient system for combining complementary kernels in complex visual categorization tasks
Lists
Only you see this
Abstract
Recently, increasing interest has been brought to improve image categorization performances by combining multiple descriptors. However, very few approaches have been proposed for combining features based on complementary aspects, and evaluating the performances in realistic databases. In this paper, we tackle the problem of combining different feature types (edge and color), and evaluate the performance gain in the very challenging VOC 2009 benchmark. Our contribution is three-fold. First, we propose new local color descriptors, unifying edge and color feature extraction into the “Bag Of Word” model. Second, we improve the Spatial Pyramid Matching (SPM) scheme for better incorporating spatial information into the similarity measurement. Last but not least, we propose a new combination strategy based on ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> Multiple Kernel Learning (MKL) that simultaneously learns individual kernel parameters and the kernel combination. Experiments prove the relevance of the proposed approach, which outperforms baseline combination methods while being computationally effective.
BibTeX
@inproceedings{picard2010efficient,
author = {David Picard and Nicolas Thome and Matthieu Cord},
title = {{An efficient system for combining complementary kernels in complex visual categorization tasks}},
booktitle = {ICIP},
year = {2010},
doi = {10.1109/icip.2010.5651051},
}Loading related content...