Scale selection properties of generalized scale-space interest point detectors
Journal of Mathematical Imaging and Vision, volume 46, number 2, pages 177-210, 2013.
Digitally published with DOI:10.1007/s10851-012-0378-3 in September 2012.
AbstractScale-invariant interest points have found several highly successful applications in computer vision, in particular for image-based matching and recognition.
This paper presents a theoretical analysis of the scale selection properties of a generalized framework for detecting interest points from scale-space features presented in Lindeberg (Int. J. Comput. Vis. 2010, under revision) and comprising:
A theoretical analysis of the sensitivity to affine image deformations is presented, and it is shown that the scale estimates obtained from the determinant of the Hessian operator are affine covariant for an anisotropic Gaussian blob model. Among the other purely second-order operators, the Hessian feature strength measure I has the lowest sensitivity to non-uniform scaling transformations, followed by the Laplacian operator and the Hessian feature strength measure II. The predictions from this theoretical analysis agree with experimental results of the repeatability properties of the different interest point detectors under affine and perspective transformations of real image data. A number of less complete results are derived for the level curve curvature operator.
PDF: (2.7 Mb)
On-line version: (At the official site of JMIV)
Background and related material: (Integration with local image descriptors for image matching and object recognition) (Earlier paper on Laplacian and determinant of the Hessian interest points with automatic scale selection)
Responsible for this page: Tony Lindeberg