GRAPH BASED DESCRIPTOR EVALUATION TOWARDS AUTOMATIC FEATURE SELECTION
Anita Keszler, Levente Kovács, Tamás Szirányi
2012
Abstract
This paper presents the first steps towards an automated image and video feature descriptor evaluation framework, based on several points of view. First, evaluation of distance distributions of images and videos for several descriptors are performed, then a graph-based representation of database contents and evaluation of the appearance of the giant component is performed. The goal is to lay the foundations for an evaluation framework where different descriptors and their combinations can be analyzed, with the goal of later application for automatic feature selection.
DownloadPaper Citation
in Harvard Style
Keszler A., Kovács L. and Szirányi T. (2012). GRAPH BASED DESCRIPTOR EVALUATION TOWARDS AUTOMATIC FEATURE SELECTION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 375-380. DOI: 10.5220/0003868503750380
in Bibtex Style
@conference{visapp12,
author={Anita Keszler and Levente Kovács and Tamás Szirányi},
title={GRAPH BASED DESCRIPTOR EVALUATION TOWARDS AUTOMATIC FEATURE SELECTION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={375-380},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003868503750380},
isbn={978-989-8565-03-7},
}
in EndNote Style
TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - GRAPH BASED DESCRIPTOR EVALUATION TOWARDS AUTOMATIC FEATURE SELECTION
SN - 978-989-8565-03-7
AU - Keszler A.
AU - Kovács L.
AU - Szirányi T.
PY - 2012
SP - 375
EP - 380
DO - 10.5220/0003868503750380