FEATURE-DRIVEN MAXIMALLY STABLE EXTREMAL REGIONS

P. Martins, C. Gatta, P. Carvalho

2012

Abstract

The high repeatability of Maximally Stable Extremal Regions (MSERs) on structured images along with their suitability to be combined with either photometric or shape descriptors to solve image matching problems have contributed to establish the MSER detector as one of the most prominent affine covariant detectors. However, the so-called affine covariance that characterizes MSERs relies on the assumption that objects possess smooth boundaries, a premiss that is not always valid. We introduce an alternative domain for MSER detection in which boundary-related features are highlighted and simultaneously delineated under smooth transitions. Detection results on common benchmarks show improvements that are discussed.

Paper Citation

in Harvard Style

Martins P., Gatta C. and Carvalho P. (2012). FEATURE-DRIVEN MAXIMALLY STABLE EXTREMAL REGIONS . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 490-497. DOI: 10.5220/0003869204900497

in Bibtex Style

@conference{visapp12,
author={P. Martins and C. Gatta and P. Carvalho},
title={FEATURE-DRIVEN MAXIMALLY STABLE EXTREMAL REGIONS},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={490-497},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003869204900497},
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 - FEATURE-DRIVEN MAXIMALLY STABLE EXTREMAL REGIONS
SN - 978-989-8565-03-7
AU - Martins P.
AU - Gatta C.
AU - Carvalho P.
PY - 2012
SP - 490
EP - 497
DO - 10.5220/0003869204900497