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

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.

Authors and Affiliations

1. Computer Vision Lab, Swiss Federal Institute of Technology, Zürich, Switzerland

   Hao Shao, Tomáš Svoboda1 & Luc Van Gool

2. ESAT, PSI, Katholieke Universiteit Leuven, Leuven, Belgium

   Tinne Tuytelaars & Luc Van Gool

Editors and Affiliations

1. LIACS Media Lab, Leiden University, Niels Bohrweg 1, 2333 CA, Leiden, The Netherlands

   Erwin M. Bakker  & Michael S. Lew  & 

2. Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, 405 N. Mathews Avenue, Urbana, IL, 61801, USA

   Thomas S. Huang

3. University of Amsterdam, Kruislaan 403, 1098 SJ, Amsterdam, The Netherlands

   Nicu Sebe

4. Siemens Corporate Research, 755 College Road East, Princeton, NJ, 08540, USA

   Xiang Sean Zhou

Reprints and permissions

© 2003 Springer-Verlag Berlin Heidelberg

Policies and ethics