IMAGE UNDERSTANDING USING SELF-SIMILAR SIFT FEATURES

Nils Hering, Frank Schmitt, Lutz Priese

2009

Abstract

In this paper we present a new method to group self-similar SIFT features in images. The aim is to automatically build groups of all SIFT features with the same semantics in an image. To achieve this a new distance between SIFT feature vectors taking into account their orientation and scale is introduced. The methods are presented in the context of recognition of buildings. A first evaluation shows promising results.

References

  1. Bay, H., Tuytelaars, T., and Van Gool, A. (2006). Surf: Speeded up robust features. In 9th European Conference on Computer Vision, Graz Austria.
  2. Chum, O. and Matas, J. (2005). Matching with prosac - progressive sample consensus. In CVPR (1), pages 220-226.
  3. Fischler, M. and Bolles, R. (1987). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. pages 726-740.
  4. Goshen, L. and Shimshoni, I. (2006). Balanced exploration and exploitation model search for efficient epipolar geometry estimation. In ECCV06, pages II: 151-164.
  5. Ke, Y. and Sukthankar, R. (2004). Pca-sift: A more distinctive representation for local image descriptors.
  6. Lowe, D. (1999). Object recognition from local scaleinvariant features. In Proc. of the International Conference on Computer Vision ICCV, Corfu, pages 1150-1157.
  7. Lowe, D. (2003). Distinctive image features from scaleinvariant keypoints. In International Journal of Computer Vision, volume 20, pages 91-110.
  8. Slot, K. and Kim, H. (2006). Keypoints derivation for object class detection with sift algorithm. In Artificial Intelligence and Soft Computing ICAISC 2006. Springer Berlin , Heidelberg.
Download


Paper Citation


in Harvard Style

Hering N., Schmitt F. and Priese L. (2009). IMAGE UNDERSTANDING USING SELF-SIMILAR SIFT FEATURES . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 114-119. DOI: 10.5220/0001753501140119


in Bibtex Style

@conference{visapp09,
author={Nils Hering and Frank Schmitt and Lutz Priese},
title={IMAGE UNDERSTANDING USING SELF-SIMILAR SIFT FEATURES},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={114-119},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001753501140119},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)
TI - IMAGE UNDERSTANDING USING SELF-SIMILAR SIFT FEATURES
SN - 978-989-8111-69-2
AU - Hering N.
AU - Schmitt F.
AU - Priese L.
PY - 2009
SP - 114
EP - 119
DO - 10.5220/0001753501140119