Abstract
We investigate the topological structure of an image and the hierarchical relationship between local and global structures provided by spatial gradients at different levels of scale. The gradient field curves link stationary points of the image including a local minimum at infinity, and construct the topological structure of the image. The evolution of the topological structure with respect to scale is analysed using pseudograph representation. The hierarchical relationships among the structures at different scales are expressed as trajectories of the stationary points in the scale space, which we call stationary curves. Each toppoint of the local extremum curve generically has a specific gradient field curve, which we call the antidirectional figure-flow curve. The antidirectional figure-flow curve connects between the toppoint and another local extremum to which the toppoint is subordinate. A point at infinity can also be connected to the toppoints of local minimum curves. These hierarchical relationships among the stationary points are expressed as a tree. As an application, we present the temporal segmentation of an image sequence based on the transition of the hierarchical structure.
Similar content being viewed by others
References
Brain Web, http://www.bic.mni.mcgill.ca/brainweb/
Computer Vision Laboratory at UMass, http://vis-www.cs.umass.edu/vislib/Motion/box/images.html
Damon, J.: Local Morse theory for solutions to the heat equation and Gaussian blurring. J. Differ. Equations 115(2), 368–401 (1995)
Damon, J.: Generic properties of solutions to partial differential equations. Arch. Ration. Mech. Analysis 140, 353–403 (1997)
Florack, L.M.J., Kuijper, A.: The topological structure of scale-space images. J. Math. Imaging Vis. 12(1), 65–79 (2000)
Griffin, L.D., Colchester, A.C.F.: Superficial and deep structure in linear diffusion scale space: Isophotes, critical points and separatrices. Image Vis. Comput. 13(7), 543–557 (1995)
Griffin, L.D., Colchester, A.C.F., Robinson, G.P.: Scale and segmentation of grey-level images using maximum gradient paths. Image Vis. Comput. 10(6), 389–402 (1992)
Iijima, T.: Basic theory on the normalization of pattern (in case of typical one-dimensional pattern). Bull. Electro-tech. Lab. 26, 368–388 (1962) (in Japanese)
Iijima, T.: Basic theory on the normalization of two-dimensional visual pattern. IEICE Jpn. 1, 15–22 (1963) (in Japanese)
Iijima, T.: Basic equation of figure and observational transformations. IEICE Jpn. Trans. C. 54-C, 37–38 (1971)
Iijima, T.: Pattern Recognition. Corona Publisher, Tokyo (1973) (in Japanese)
Iijima, T.: The Fundamental Theory of Visual Information: The Foundation of the Pattern Recognition Problem. Corona Publisher, Tokyo (1999)
Imiya, A., Sugiura, T., Sakai, T., Kato, Y.: Temporal structure tree in digital linear scale space. In: Lecture Notes in Computer Science, vol. 2695, pp. 356–371. Springer, New York (2003)
Johansen, P.: On the classification of toppoints in scale space. J. Math. Imaging Vis. 4(1), 57–67 (1994)
Johansen, P., Skelboe, S., Grue, K., Andersen, J.D.: Representing signals by their toppoints in scale space. In: Proc. of Int. Conf. on Imag. Anal. and Pat. Recog., Paris, France, pp. 215–217 (1986)
Koenderink, J.J.: The structure of images. Biol. Cybern. 50, 363–370 (1984)
Koenderink, J.J.: Solid Shape. MIT Press, Cambridge (1990)
Kuijper, A.: The deep structure of Gaussian scale space images. PhD thesis, Utrecht University (2002)
Kuijper, A., Florack, L.M.J., Viergever, M.A.: Scale space hierarchy. J. Math. Imaging Vis. 18(2), 169–189 (2003)
Lifshitz, L.M., Pizer, S.M.: A multiresolution hierarchical approach to image segmentation based on intensity extrema. IEEE Trans. Pattern Analysis Mach. Intell. 12(6), 529–540 (1990)
Lindeberg, T.: Scale-Space Theory in Computer Vision. Kluwer Academic, Boston (1994)
Loog, M., Duistermaat, J.J., Florack, L.M.J.: On the behavior of spatial critical points under Gaussian blurring. In: Lecture Notes in Computer Science, vol. 2106, pp. 183–192. Springer, New York (2001)
Olsen, O.F., Nielsen, M.: Generic events for the gradient squared with application to multi-scale segmentation. In: Lecture Notes in Computer Science, vol. 1252, pp. 101–112. Springer, New York (1997)
Otsu, N.: Mathematical studies on feature extraction in pattern recognition. Researches of The Electrotechnical Laboratory 818 (1981) (in Japanese)
Sakai, T., Imiya, A.: Figure field analysis of linear scale-space image. In: Lecture Notes in Computer Science, vol. 3459, pp. 374–385. Springer, New York (2005)
Sakai, T., Imiya, A.: Scale-space hierarchy of singularities. In: Lecture Notes in Computer Science, vol. 3753, pp. 181–192. Springer, New York (2005)
Simmons, A., Arridge, S.R., Tofts, P.S., Barker, G.J.: Application of the Extremum Stack to Neurological MRI. IEEE Trans. Med. Imaging 17(3), 371–382 (1998)
Weickert, J., Ishikawa, S., Imiya, A.: On the history of Gaussian scale-space axiomatics. In: Gaussian Scale-Space Theory. Computational Imaging and Vision Series, vol. 8, pp. 45–59. Kluwer Academic, Dordrecht (1997)
Weickert, J., Ishikawa, S., Imiya, A.: Linear scale-space has first been proposed in Japan. J. Math. Imaging Vis. 10(3), 237–252 (1999)
Witkin, A.P.: Scale space filtering. In: Proc. of 8th Int. Joint Conf. on Artif. Intell., pp. 1019–1022. Karlsruhe, West Germany (1983)
Zhao, N.-Y., Iijima, T.: Theory on the method of determination of view-point and field of vision during observation and measurement of figure. IEICE Jpn. Trans. D J68-D, 508–514 (1985) (in Japanese)
Zhao, N.-Y., Iijima, T.: A theory of feature extraction by the tree of stable view-points. IEICE Jpn. Trans. D J68-D, 1125–1135 (1985) (in Japanese)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sakai, T., Imiya, A. Gradient Structure of Image in Scale Space. J Math Imaging Vis 28, 243–257 (2007). https://doi.org/10.1007/s10851-007-0005-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-007-0005-x