Abstract
The formulation of afront-end or“early vision” system is addressed, and its connection with scale-space is shown. A front-end vision system is designed to establish a convenient format of some sampled scalar field, which is suited for postprocessing by various dedicated routines. The emphasis is on the motivations and implications of symmetries of the environment; they pose natural, a priori constraints on the design of a front-end.
The focus is on static images, defined on a multidimensional spatial domain, for which it is assumed that there are no a priori preferred points, directions, or scales. In addition, the front-end is required to be linear. These requirements are independent of any particular image geometry and express the front-end's pure syntactical, “bottom up” nature.
It is shown that these symmetries suffice to establish the functionality properties of a front-end. For each location in the visual field and each inner scale it comprises a hierarchical family of tensorial apertures, known as the Gaussian family, the lowest order of which is the normalised Gaussian. The family can be truncated at any given order in a consistent way. The resulting set constitutes a basis for alocal jet bundle.
Note that scale-space theory shows up here without any call upon the “prohibition of spurious detail”, which, in some way or another, usually forms the basic starting point for “diffusion-like” scale-space theories.
Similar content being viewed by others
References
J. Babaud, A.P. Witkin, M. Baudin, and R.O. Duba, “Uniqueness of the gaussian kernel for scale-space filtering,”IEEE Trans. Pattern Analysis and Machine Intelligence, 8(1):26–33, 1986.
Piet Bijl,Aspects of Visual Contrast Detection. PhD thesis, University of Utrecht, The Netherlands, May 1991.
J. Blom, B.M. ter Haar Romeny, A. Bel, and J.J. Koenderink, “Spatial derivatives and the propogation of noise in gaussian scale-space,”J. of Vis. Comm. and Im. Repr., 4(1):1–13, March 1993.
P.J. Burt, T.H. Hong, and A. Rosenfeld, “Segmentation and estimation of image region properties through cooperative hierarchical computation,”IEEE Trans. Systems, Man, and Cybernetics, 11(12):802–825, 1981.
J.L. Crowley, “Towards continuously operating integrated vision systems for robotics applications,” In Peter Johnsen and Søren Olsen, editors,Proc. 7th Scand. Conf. on Image Analysis, pages 494–505, Aalborg, DK, August 13–16 1991.
J.L. Crowley, A. Chehikian, and F. Veillon, “Definition of image primitives,” VAP Tech. Rep. IR.A.3.1, LIFIA (IMAG)-I.N.P., Grenoble, France, 1990.
James Damon, “Local Morse theory for solutions to the heat equation and Gaussian blurring,” Internal report Department of Mathematics. University of North Carolina, Chapel Hill, North Carolina, USA, 1990.
Burkart Fischer, “Overlap of receptive field centers and representation of the visual field in the cat's optic tract,”Vision Research, 13:2113–2120, 1973.
L.M.J. Florack, B.M. ter Haar Romeny, J.J. Koenderink, and M.A. Viergever, “Scale and the differential structure of iamges,”Image and Vision Computing, 10(6):376–388, July/August 1992.
L.M.J. Florack, B.M. ter Haar Romeny, J.J. Koenderink, and M.A. Viergever, “Cartesian differential invariants in scale-space,”Journal of Mathematical Imaging and Vision, 3(4):327–348, November 1993.
L.M.J. Florack, B.M. ter Haar Romeny, J.J. Koenderink, and M.A. Viergever, “General intensity transformations and differential invariants,”Journal of Mathematical Imaging and Vision, 1993. Accepted.
Joseph Fourier.The Analytical Theory of Heat. Dover Publications, Inc. New York, 1955. Replication of the English translation that first appeared in 1878 with previous corrigenda incorporated into the text, by Alexander Freeman, M.A. Original work: “Théorie Analytique de la Chaleur,” Paris, 1822.
David H. Hubel.Eye, Brain and Vision, volume 22 ofScientific American Library, Scientific American Press, New York, 1988.
R.A. Hummel and B.C. Gidas, “Zero crossings and the heat equation,”Technical Report 111, New York Univ. Courant Institute of Math. Sciences, Computer Science Division, 1984.
R.A. Hummel, B.B. Kimia, and S.W. Zucker, “Deblurring Gaussian blur,”Computer Vision, Graphics, and Image Processing, 38:66–80, 1987.
B.B. Kimia,Deblurring gaussian blur, continuous and discrete approaches, Master's thesis, McGill University, Electrical Eng. Dept., Montreal, Canada, 1986.
J.J. Koenderink, “The concept of local sign,” in A.J. vanDoorn, W.A. van de Grind, and J.J. Koenderink, editors,Limits in Perception, pages 495–547. VNU Science Press, Utrecht, 1984.
J.J. Koenderink, “The structure of images,”Biol. Cybern., 50:363–370, 1984.
J.J. Koenderink, “The structure of the visual field,” in W. Güttinger, and G. Dangelmayr, editors,The Physics of Structure Formation, Theory and Simulation. Springer-Verlag, 1986. Proceedings of an International Symposium, tübingen, Fed. Rep. of Germany, October 27–November 2.
J.J. Koenderink, “Scale-time,”Biol. Cybern., 58:159–162, 1988.
J.J. Koenderink,Solid Shape, MIT Press, Cambridge, Mass., 1990.
J.J. Koenderink, “Local image structure,” inProc. Scand Conf. on Image Analysis, pages 1–7, Aalborg, DK, August 1991.
J.J.Koenderink and A.J. van Doorn, “Representation of local geometry in the visual system,”Biol. Cybern., 55:367–375, 1987.
J.J. Koenderink and A.J. van Doorn, “Receptive field families,”Biol. Cybern., 63:291–298, 1990.
L.M. Lifshitz and S.M. Pizer, “A multiresolution hierarchical approach to image segmentation based on intensity extrema,”IEEE Trans. Pattern Analysis and Machine Inteligence, 12(6):529–541, 1990.
Alan P. Lightman, William H. Press, Richard H. Price, and Saul A. Teukolsky,Problem Book in Relativity and Gravitation, Princeton University Press, Princeton, New Jersey, 1975.
T. Lindeberg, “Scale-space for discrete signals,”IEEE Trans. Pattern Analysis and Machine Intelligence, 12(3):234–245, 1990.
T. Lindeberg,Discrete Scale-Space Theory and the Scale-Space Primal Sketch, PhD thesis, Royal Institute of Technology, Department of Numerical Analysis and Computing Science, Royal Institute of Technology, S-100 44 Stockholm, Sweden, May 1991.
T. Lindeberg and J.O. Eklundh, “Guiding early visual processing with a scale-space primal sketch,”Technical Report CVAP-72, Royal Institute of Technology, University of Stockholm, Dept. of Numerical Analysis and Computing Science, Stockholm, Sweden, 1990.
T. Lindeberg and J.O. Eklundh, “On the computation of a scale-space primal sketch,” Technical Report CVAP-68, Royal Institute of Technology, University of Stockholm, Dept. of Numerical Analysis and Computing Science, Stockholm, Sweden, 1990.
M.M. Lipschutz,Differential Geometry, Schaum's Outline Series. McGraw Hill, New York, 1969.
Lord Rayleigh, “The principle of similitude,”Nature, XCV:66–68, 644, March 1915.
S.G. Mallat, “A theory of multiresolution signal decomposition: The wavelet representation,”IEEE Trans. Pattern Analysis and Machine Intelligence, 11(7):674–694, 1989.
J.B. Martens, “Deblurring digital images by means of polynomial transforms,”Computer Vision, Graphics, and Image and Stochastic Processing, 50:157–176, 1990.
H.E. Moses and A.F. Quesada, “The expansion of physical quantities in terms of the irreducible representations of the scale-euclidean group and applications to the construction of the scale-invariant correlation functions,”Arch. Rat. Mech. Anal., 44:217–248, 1971, Part I. Concepts. One-Dimensional Problems, Communicated by J. Meixner.
H.E. Moses and A.F. Quesada, “The expansion of physical quantities in terms of the irreducible representations of the scale-euclidean group and applications to the construction of scale-invariant correlation functions,”Arch. Rat. Mech. Anal., 50:194–236, 1973. Part II. Three-Dimensional Problems; Generalizations of the Helmholtz Vector Decomposition Theorem, Communicated by J. Meixner.
P.J. Olver,Applications of Lie Groups to Differential Equations, volume 107 ofGraduate Texts in Mathematics, Springer-Verlag, 1986.
S.M. Pizer, J.J. Koenderink, L.M. Lifshitz, L. Helmink, and A.D.J. Kaasjager, “An image description for object defintion, based on extremal regions in the stack,”Information Processing in Medical Imaging, Proceedings of the 8th conference, pages 24–37, 1985.
T. Poston and I. Steward,Catastrophe Theory and its Applications, Pitman, London, 1978.
M. Spivak,A Comprehensive Introduction to Differential Geometry, volume I–V, Publish or Perish, Inc., Houston, Texas, 1970.
B.M. ter Haar Romeny and L.M.J. Florack, “A multiscale geometric model of human vision, “In William R. Hendee and Peter N.T. Wells, editors,Perception of Visual Information, chapter 4, pages 73–114. Springer-Verlag, Berlin, 1993.
B.M. ter Haar Romeny and L.M.J. Florack, J.J. Koenderink, and M.A. Viergever, “Scale-space: Its natural operators and differential invariants,” in A.C.F. Colchester and D.J. Hawkes, editors,Information Processing in Medical Imaging, volume 511 ofLecture Notes in Computer Science, pages 239–255, Berlin, July 1991, Springer-Verlag.
Massimo Tistarelli and Giulio Sandini, Dynamic aspects in active vision,”CVGIP: Image Understanding, 56(1):108–129, July 1992.
A.J. van Door, J.J. Koenderink, and M.A. Bouman, “The influence of the retinal inhomogeneity on the perception of spatial patterns,”Kybernetik, 10:223–230, 1972.
H. Wässle, U. Grünert, J. Röhrenbeck, and B. Boycott, “Retinal ganglion cell density and cortical magnification factor in the primat,”Vision Research, 30:1897–1911, 1990.
H. Weyl,The Classical Groups, their Invariants and Representations, Princeton University Press, Princeton, NJ, 1946.
A.P. Witkin. “Scale space filtering,” inProc. International Joint Conference on Artificial Intelligence, pages 1019–1023, Karlsruhe, W. Germany, 1983.
R.A. Young. The Gaussian derivative theory of spatial vision: Analysis of cortical cell receptive field line-weighting profiles. Publication gmr-4920, General Motors Research Labs, Computer Science Dept., 30500 Mound Road, Box 9055, Warren, Michigan 48090-9055, May 28 1985.
R.A. Young, “The Gaussian derivative model for machine vision: Visual cortex simulation,”Journal of the Optical Society of America, July 1986.
R.A. Young, “Simulation of human retinal function with the Gaussian derivative model,” inProc. IEEE CVPR CH2290-5, pages 564–569, Miami, Fla. 1986.
A.L. Yuille and T.A. Poggio, “Scaling theorems for zerocrossings,”IEEE Trans. Pattern Analysis and Machine Intelligence, 8:15–25, 1986.
A.L. Yuille and T.A. Paggio, “Scaling and fingerprint theorems for zero-crossings,” in C. Brown, editor,Advances in Computer Vision, pages 47–78. Lawrence Erlbaum, 1988.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Florack, L.M.J., ter Haar Romeny, B.M., Koenderink, J.J. et al. Linear scale-space. J Math Imaging Vis 4, 325–351 (1994). https://doi.org/10.1007/BF01262401
Issue Date:
DOI: https://doi.org/10.1007/BF01262401