Abstract
A method which detects the characteristic shapes and sizes of image structures is proposed. The idea of the principal curvature plane is introduced in order to observe the change of the principal curvatures, and to select the scales at which the shape of the local profile becomes the sharpest. We extract points which are shape representational points at the selected scales as the feature points. The experimental results show that this method extracts features of image structures successfully.
Preview
Unable to display preview. Download preview PDF.
References
Jan J. Koenderink. Solid Shape. The MIT Press, 1990.
Tony Lindeberg. Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, 1994.
Tony Lindeberg. Edge Detection and Ridge Detection with Automatic Scale Selection. In Proc. of Computer Vision and Pattern Recognition (San Francisco), pp.465–470, 1996.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hontani, H., Deguchi, K. (1997). Multi-scale detection of characteristic figure structures using principal curvatures of image gray-level profile. In: ter Haar Romeny, B., Florack, L., Koenderink, J., Viergever, M. (eds) Scale-Space Theory in Computer Vision. Scale-Space 1997. Lecture Notes in Computer Science, vol 1252. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63167-4_61
Download citation
DOI: https://doi.org/10.1007/3-540-63167-4_61
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63167-5
Online ISBN: 978-3-540-69196-9
eBook Packages: Springer Book Archive