, Volume 65, Issue 1-2, pp 43-72
Date: 14 Oct 2005

A Comparison of Affine Region Detectors

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access

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.

First online version published in October, 2005