Advertisement

HPAT Indexing for Fast Object/Scene Recognition Based on Local Appearance

  • Hao Shao
  • Tomáš Svoboda1
  • Tinne Tuytelaars
  • Luc Van Gool
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2728)

Abstract

The paper describes a fast system for appearance based image recognition. It uses local invariant descriptors and efficient nearest neighbor search. First, local affine invariant regions are found nested at multiscale intensity extremas. These regions are characterized by nine generalized color moment invariants. An efficient novel method called HPAT (hyper-polyhedron with adaptive threshold) is introduced for efficient localization of the nearest neighbor in feature space.

The invariants make the method robust against changing illumination and viewpoint. The locality helps to resolve occlusions. The proposed indexing method overcomes the drawbacks of most binary tree-like indexing techniques, namely the high complexity in high dimensional data sets and the boundary problem. The database representation is very compact and the retrieval close to realtime on a standard PC. The performance of the proposed method is demonstrated on a public database containing 1005 images of urban scenes. Experiments with an image database containing objects are also presented.

Keywords

Feature Vector Query Image Query Point Invariant Region Candidate List 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    A. Baumberg. Reliable feature matching across widely separated views. In Computer Vision and Pattern Recognition, pages 774–781, 2000Google Scholar
  2. [2]
    Krystian Mikolajczyk and Cordelia Schmid. An affune invariant interest points detector. In European Conference on Computer Vision, pages 128–142, 2002Google Scholar
  3. [3]
    F. Mindru, T. Moons, and L. Van Gool. Recognizing color patterns irrespective of viewpoint and illumination. In Computer Vision and Pattern Recognition, pages 368–373, 1999Google Scholar
  4. [4]
    Sameer A. Nene and Shree K. Nayar. A simple algorithm for nearest neighbor search in high dimensions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19, 1997Google Scholar
  5. [5]
    J. Matas O. Chum, M. Urban and T. Pajdla. Robust wide baseline stereo from maximally stable extremal regions. In British Machine Vision Conference, 2002Google Scholar
  6. [6]
    Hao Shao, Tomáš Svoboda, and Luc Van Gool. ZuBuD — Zörich buildings database for image based recognition. Technical Report 260, Computer Vision Laboratory, Swiss Federal Institute of Technology, March 2003. Database downloadable from http://www.vision.ee.ethz.ch/showroom/Google Scholar
  7. [7]
    T. Tuytelaars and Van Gool. Wide baseline stero based on local affinely invariant regions. In British Machine Vision Conference, 2000Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Hao Shao
    • 1
  • Tomáš Svoboda1
    • 1
  • Tinne Tuytelaars
    • 2
  • Luc Van Gool
    • 1
    • 2
  1. 1.Computer Vision LabSwiss Federal Institute of TechnologyZürichSwitzerland
  2. 2.ESAT, PSIKatholieke Universiteit LeuvenLeuvenBelgium

Personalised recommendations