Abstract
Blurring an image with a Gaussian of width σ and considering σ as an extra dimension, extends the image to an Gaussian scale space (\(\mathcal{GSS}\)) image. In this \(\mathcal{GSS}\)-image the iso-intensity manifolds behave in an nicely pre-determined manner. As a result of that, the \(\mathcal{GSS}\)-image directly generates a hierarchy in the form of a binary ordered rooted tree, that can be used for segmentation, indexing, recognition and retrieval. Understanding the geometry of the manifolds allows fast methods to derive the hierarchy. In this paper we discuss the relevant geometric properties of \(\mathcal{GSS}\) images, as well as their implications for algorithms used for the tree extraction. Examples show the applicability and increased speed of the proposed method compared to traditional ones.
This work is part of the DSSCV project supported by the IST Programme of the European Union (IST-2001-35443). WWW home page: http://www.itu.dk/Internet/sw1953.asp
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Damon, J.: Local Morse theory for solutions to the heat equation and Gaussian blurring. Journal of Differential Equations 115(2), 386–401 (1995)
Florack, L.M.J.: Image Structure. Computational Imaging and Vision Series, vol. 10. Kluwer Academic Publishers, Dordrecht (1997)
Griffin, L.D., Colchester, A.: Superficial and deep structure in linear diffusion scale space: Isophotes, critical points and separatrices. Image and Vision Computing 13(7), 543–557 (1995)
Griffin, L.D., Lillholm, M. (eds.): Scale-Space 2003. LNCS, vol. 2695. Springer, Heidelberg (2003)
ter Haar Romeny, B.M.: Front-end vision and multi-scale image analysis. Computational Imaging and Vision Series, vol. 27. Kluwer Academic Publishers, Dordrecht (2003)
Iijima, T.: On the Gaussian scale-space. IEICE Japan, Trans. D E86-D(7), 1162–1164 (2003)
Kanters, F., Platel, B., Florack, L.M.J., ter Haar Romeny, B.M.: Content based image retrieval using multiscale top points. In: Griffin and Lillholm [4], pp. 33–43 (2003)
Kerckhove, M. (ed.): Scale-Space 2001. LNCS, vol. 2106. Springer, Heidelberg (2001)
Koenderink, J.J.: The structure of images. Biological Cybernetics 50, 363–370 (1984)
Koenderink, J.J.: A hitherto unnoticed singularity of scale-space. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(11), 1222–1224 (1989)
Kuijper, A., Florack, L.M.J.: Hierarchical pre-segmentation without prior knowledge. In: Proceedings of the 8th International Conference on Computer Vision, Vancouver, Canada, July 9-12, pp. 487–493 (2001)
Kuijper, A., Florack, L.M.J.: The hierarchical structure of images. IEEE Transactions on Image Processing 12(9), 1067–1079 (2003)
Lifshitz, L.M., Pizer, S.M.: A multiresolution hierarchical approach to image segmentation based on intensity extrema. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(6), 529–540 (1990)
Lindeberg, T.: Scale-Space Theory in Computer Vision. The Kluwer International Series in Engineering and Computer Science. Kluwer Academic Publishers, Dordrecht (1994)
Loog, M., Duistermaat, J.J., Florack, L.M.J.: On the behavior of spatial critical points under Gaussian blurring, a folklore theorem and scale-space constraints. In: Kerckhove [8], pp. 183–192 (2001)
Schwartz, L.: Théorie des Distributions, Actualités scientifiques et industrielles; 1091,1122. vol. I, II. Publications de l’Institut de Mathématique de l’Université de Strasbourg, Paris, 1950–1951
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kuijper, A. (2005). Exploiting Deep Structure. In: Fogh Olsen, O., Florack, L., Kuijper, A. (eds) Deep Structure, Singularities, and Computer Vision. DSSCV 2005. Lecture Notes in Computer Science, vol 3753. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11577812_15
Download citation
DOI: https://doi.org/10.1007/11577812_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29836-6
Online ISBN: 978-3-540-32097-5
eBook Packages: Computer ScienceComputer Science (R0)