Abstract
We propose a novel method for performing point-feature correspondence based on a modal shape description. Introducing shape information into a low-level matching process allows our algorithm to cope easily with rotations and translations in the image plane, yet still give a dense correspondence. We also show positive results for scale changes and small skews, and demonstrate how reflectional symmetries can be detected.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G.L. Scott and H.C. Longuet-Higgins, “An algorithm for associating the features of two patterns”, Proceedings of the Royal Society of London, Vol. B244, 1991, pp. 21–26.
S. Ullman, The Interpretation of Visual Motion, MIT Press, USA, 1979.
L.S. Shapiro. “Towards a Vision-Based Motion Framework”, First Year Report, Department of Engineering Science, Oxford University, May 1991.
G.L. Scott and H.C. Longuet-Higgins, “Feature grouping by ‘relocalisation’ of eigenvectors of the proximity matrix”, Proceedings of the British Machine Vision Conference (BMVC90), Oxford University, Sept. 1990, pp. 103-108.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag London Limited
About this paper
Cite this paper
Shapiro, L.S., Brady, J.M. (1991). A Modal Approach to Feature-based Correspondence. In: Mowforth, P. (eds) BMVC91. Springer, London. https://doi.org/10.1007/978-1-4471-1921-0_11
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1921-0_11
Publisher Name: Springer, London
Print ISBN: 978-3-540-19715-7
Online ISBN: 978-1-4471-1921-0
eBook Packages: Springer Book Archive