A Comparison of Affine Region Detectors

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.

DOI: 10.1007/s11263-005-3848-x

Extracted Key Phrases

0100200'05'06'07'08'09'10'11'12'13'14'15'16'17
Citations per Year

2,376 Citations

Semantic Scholar estimates that this publication has 2,376 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Mikolajczyk2005ACO, title={A Comparison of Affine Region Detectors}, author={Krystian Mikolajczyk and Tinne Tuytelaars and Cordelia Schmid and Andrew Zisserman and Jiri Matas and Frederik Schaffalitzky and Timor Kadir and Luc Van Gool}, journal={International Journal of Computer Vision}, year={2005}, volume={65}, pages={43-72} }