A Comparison of Affine Region Detectors

  • Authors:

  • K. Mikolajczyk;T. Tuytelaars;C. Schmid;A. Zisserman;J. Matas;F. Schaffalitzky;T. Kadir;L. Van Gool

  • Affiliations:

  • University of Oxford, Oxford, United Kingdom OX1 3PJ;University of Leuven, Leuven, Belgium;INRIA, GRAVIR-CNRS, Montbonnot, France 38330;University of Oxford, Oxford, United Kingdom OX1 3PJ;Czech Technical University, Prague, Czech Republic 121 35;University of Oxford, Oxford, United Kingdom OX1 3PJ;University of Oxford, Oxford, United Kingdom OX1 3PJ;University of Leuven, Leuven, Belgium

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper gives a snapshot of the state of the art in affine covariant region detectors, and compares their performance on a set of test images under varying imaging conditions. Six types of detectors are included: detectors based on affine normalization around Harris (Mikolajczyk and Schmid, 2002; Schaffalitzky and Zisserman, 2002) and Hessian points (Mikolajczyk and Schmid, 2002), a detector of `maximally stable extremal regions', proposed by Matas et al. (2002); an edge-based region detector (Tuytelaars and Van Gool, 1999) and a detector based on intensity extrema (Tuytelaars and Van Gool, 2000), and a detector of `salient regions', proposed by Kadir, Zisserman and Brady (2004). The performance is measured against changes in viewpoint, scale, illumination, defocus and image compression.The objective of this paper is also to establish a reference test set of images and performance software, so that future detectors can be evaluated in the same framework.