Accurate and Efficient Approximation of the Continuous Gaussian Scale-Space

Ullrich Köthe

in: C.E. Rasmussen, H. Bülthoff, M. Giese, B. Schölkopf (Eds.): Pattern Recognition, Proc. of 26th DAGM Symposium, Tübingen 2004, Lecture Notes in Computer Science 3175, pp. 350-358, Heidelberg: Springer, 2004 (note: this article is © Springer-Verlag)

Abstract

The Gaussian scale-space is a standard tool in image analysis. While continuous in theory, it is generally realized with fixed regular grids in practice. This prevents the use of algorithms which require continuous and differentiable data and adaptive step size control, such as numerical path following. We propose an efficient continuous approximation of the Gaussian scale-space that removes this restriction and opens up new ways to subpixel feature detection and scale adaptation.

Online version: PostScript (280 kb), PDF (148 kb)

Back to Ullrich Köthe's publication page