Dyadic scale space
Authors:
- SongDe MaSMSongDe Ma
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 399-402 vol.2
Abstract
We approximate Gaussian function with any scale by linear combination of Gaussian functions with dyadic scales so that scale space can be constructed much more efficiently. The approximation error is so small that our approach can be used widely in computer vision and pattern recognition. Features at any scale can also be found efficiently by tracking from the dyadic scales.Keywords
This publication has 11 references indexed in Scilit:
- Deformable kernels for early visionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1995
- Scale-Space Theory in Computer Vision1994
- The design and use of steerable filtersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Mach bands are phase dependentNature, 1986
- Uniqueness of the Gaussian Kernel for Scale-Space FilteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 1986
- Spatiotemporal energy models for the perception of motionJournal of the Optical Society of America A, 1985
- The structure of imagesBiological Cybernetics, 1984
- The Laplacian Pyramid as a Compact Image CodeIEEE Transactions on Communications, 1983
- Theory of edge detectionProceedings of the Royal Society of London. B. Biological Sciences, 1980
- The Shannon sampling theorem—Its various extensions and applications: A tutorial reviewProceedings of the IEEE, 1977