A Systems View of Scale Space

R. Eaton, M. Stevens, J. McBride, G. Foil, & M. Snorrason

Proceedings of International Conference on Computer Vision Systems, New York, NY (January, 2006)

Over the last 30 years, scale space representations have emerged as a fundamental tool for allowing systems to become increasingly robust against changes in camera viewpoint. Unfortunately, the implementation details that are required to properly construct a scale space representation are not published in the literature. Incorrectly implementing these details will lead to extremely poor system performance. In this paper, we address the practical considerations associated with scale space representations. Our focus is to make explicit how a scale space is constructed, thereby increasing the accessibility of this powerful representation to developers of computer vision systems.

Example half-octave pyramid with three images in each octave, shown in order of increasing blur from left to right.

Request a Copy