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.

References

  1. Dickscheid, T., Schindler, F., and F örstner, W. (2010). Coding images with local features. International Journal of Computer Vision (in press).
  2. Forssen, P.-E. and Lowe, D. (2007). Shape Descriptors for Maximally Stable Extremal Regions. In Proc. of IEEE 11th Int. Conf. on Computer Vision, pages 1-8.
  3. Kimmel, R., Zhang, C., Bronstein, A., and Bronstein, M. (2011). Are MSER features really interesting? IEEE Trans. on Pattern Analysis and Machine Intelligence, 33(11):2316-2320.
  4. Matas, J., Chum, O., Urban, M., and Pajdla, T. (2002). Robust wide baseline stereo from maximally stable extremal regions. In Proc. of the British Machine Vision Conference 2002 (BMVC 2002), pages 384-393.
  5. Mikolajczyk, K. and Schmid, C. (2004). Scale & affine invariant interest point detectors. International Journal of Computer Vision, 60(1):63-86.
  6. Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., and Gool, L. V. (2005). A Comparison of Affine Region Detectors. International Journal of Computer Vision, 65(1/2):43-72.
  7. Moreels, P. and Pietro, P. (2007). Evaluation of Features Detectors and Descriptors based on 3D Objects. Int. J. Comput. Vision, 73(3):263-284.
  8. Tuytelaars, T. and Mikolajczyk, K. (2008). Local invariant feature detectors: a survey. Found. Trends Comput. Graph. Vis., 3(3):177-280.
  9. Vedaldi, A. and Fulkerson, B. (2008). VLFeat: An open and portable library of computer vision algorithms. http://www.vlfeat.org/.
Download


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