A comparison of affine region detectors
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 [24, 34] and Hessian points , as proposed by Mikolajczyk and Schmid and by Schaffalitzky and Zisserman; a detector of ‘maximally stable extremal regions’, proposed by Matas et al. ; an edge-based region detector  and a detector based on intensity extrema , proposed by Tuytelaars and Van Gool; and a detector of ‘salient regions’, proposed by Kadir, Zisserman and Brady . 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.