SIFT-Based Object Recognition With Fast Alphabet Creation and Reduced Curse of Dimensionality (bibtex)
by Martin Stommel, Otthein Herzog
Abstract:
This article presents a SIFT-based object recognition method that avoids the typical problems of time-consuming code-book generation and curse of dimensionality in feature comparison. The first problem is solved by using an alphabet of completely synthetic feature vectors. The second problem is solved by using the Hamming-distance on binarised SIFTfeatures. The method is supported by competitive results on the Graz?02 image data base.
Reference:
Martin Stommel, Otthein Herzog, "SIFT-Based Object Recognition With Fast Alphabet Creation and Reduced Curse of Dimensionality", In Int?l Conf. on Image and Vision Computing New Zealand, Wellington, New Zealand, 2009.
Bibtex Entry:
@INPROCEEDINGS{Stommel2008a,
  author = {Stommel, Martin and Herzog, Otthein},
  title = {SIFT-Based Object Recognition With Fast Alphabet Creation and Reduced
	Curse of Dimensionality},
  booktitle = {Int?l Conf. on Image and Vision Computing New Zealand},
  year = {2009},
  address = {Wellington, New Zealand},
  month = {November23--25},
  abstract = {This article presents a SIFT-based object recognition method that
	avoids the typical problems of time-consuming code-book generation
	and curse of dimensionality in feature comparison. The first problem
	is solved by using an alphabet of completely synthetic feature vectors.
	The second problem is solved by using the Hamming-distance on binarised
	SIFTfeatures. The method is supported by competitive results on the
	Graz?02 image data base.},
  doi = {10.1109/IVCNZ.2009.5378422},
  owner = {pmania},
  timestamp = {2012.11.06},
  url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp={\&}arnumber=5378422}
}
Powered by bibtexbrowser