Skip to main content

Pattern Theory: A Unifying Perspective

  • Chapter

Part of the book series: Progress in Mathematics ((PM,volume 3))

Abstract

The term “Pattern Theory” was introduced by Ulf Grenander in the 70s as a name for a field of applied mathematics which gave a theoretical setting for a large number of related ideas, techniques and results from fields such as computer vision, speech recognition, image and acoustic signal processing, pattern recognition and its statistical side, neural nets and parts of artificial intelligence (see [Grenander 76–81]). When I first began to study computer vision about ten years ago, I read parts of this book but did not really understand his insight. However, as I worked in the field, every time I felt I saw what was going on in a broader perspective or saw some theme which seemed to pull together the field as a whole, it turned out that this theme was part of what Grenander called pattern theory. It seems to me now that this is the right framework for these areas, and, as these fields have been growing explosively, the time is ripe for making an attempt to reexamine recent progress and try to make the ideas behind this unification better known. This article presents pattern theory from my point of view, which may be somewhat narrower than Grenander’s, updated with recent examples involving interesting new mathematics.

Suppported in part by NSF Grant DMS 91-21266 and by the Geometry Center, University of Minnesota, a STC funded by NSF, DOE and Minnesota Technology Inc.

This is a preview of subscription content, log in via an institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD   54.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Bibliography

  • Ambrosio, L. and Tortorelli, V., Approximations of functional depending on jumps by elliptic functionals via gamma-convergence, Comm. Pure & Applied Math. 43 (1991), 999–1036.

    Article  MathSciNet  Google Scholar 

  • Amit, D., Modelling Brain Function, Cambridge University Press, Cambridge, 1989.

    Google Scholar 

  • Amit, Y., A non-linear variational problem for image matching, SIAM Journal on Scientific Computing, to appear.

    Google Scholar 

  • Belhumeur, P. and Mumford, D., A Bayesian Treatment of the Stereo Correspondence Problem Using Half-Occluded Regions, in Proc. IEEE Conf. Comp. Vision and Pattern Rec., 1992, 506–512.

    Google Scholar 

  • Blake, A. and Zisserman. A. Visual Reconstruction, MIT Press, Cambridge, 1987.

    Google Scholar 

  • Burt, P. and Adelson, E., The Laplacian pyramid as a compact image code, IEEE Trans, on Comm. 31 (1983), 532–540.

    Article  Google Scholar 

  • Carpenter, G. and Grossberg, S. A massively parallel architecture for a self-organizing neural pattern recognition machine, Comp. Vision, Graphics and Image Proc. 37 (1987), 54–115.

    Article  Google Scholar 

  • Cavanagh, P., What’s up in top-down processing, Proc. 13th ECVP. 1991.

    Google Scholar 

  • Coifman, R., Meyer, Y. and Wickerhouser, V. Wavelet analysis and signal processing, preprint, Yale Univ. Math. Dept. New Haven, 1990.

    Google Scholar 

  • Dal Maso, G., Morel, J-M. and Solimini, S., A Variational Method in Image Segmentation, Acta Math. 168 (1992), 89–151.

    Article  MathSciNet  MATH  Google Scholar 

  • Daubechies, I., Orthonormal bases of compactly supported wavelets, Comm. Pure & Applied Math. 49 (1988), 909–996.

    Article  MathSciNet  Google Scholar 

  • Daubechies, I., The wavelet transform, time-frequency localization and signal analysis, IEEE Trans. Inf. Theory, 1990, 961–1005.

    Google Scholar 

  • DeGiorgi, E., Carriero, M. and Leaci, A., Existence theorem for a minimum problem with free discontinuity set, Arch. Rat. Mech. Anal. 108 (1989), 195–218.

    Article  MathSciNet  Google Scholar 

  • Dowling, J., The Retina, Harvard University Press, Cambridge, 1987.

    Google Scholar 

  • Findler, N. ed., Associative Networks, Academic Press, New York, 1979.

    MATH  Google Scholar 

  • Fischler, M. and Elschlager, R., The Representation and Matching of Pictorial Structures, in IEEE Trans, on Computers 22 (1973), 67–92.

    Article  Google Scholar 

  • Gage, M. and Hamilton, R., The heat equation shrinking convex plane curves, J. Diff. Geom. 23 (1986), 69–96.

    MathSciNet  MATH  Google Scholar 

  • Geiger, D. and Yuille, A., A Common Framework for Image Segmentation, Int. J. Comp. Vision, 1990.

    Google Scholar 

  • Geiger, D., Ladendorf, B. and Yuille, A., Occlusions and Binocular Stereo, in Proc. European Conf. Comp. Vision, 588 (1992), Springer Lecture Notes in Computer Sciences, Berlin-Heidelberg.

    Google Scholar 

  • Geman, D., Random Fields and Inverse Problems in Imaging, Springer Lecture Notes in Math. 1427 (1991), Berlin-Heidelberg-New York.

    Google Scholar 

  • Geman, S. and Geman, D., Stochastic relaxation, Gibbs distribution and Bayesian restoration of images, IEEE Trans. Pattern Anal. Mach. Intell. 6 (1984), 721–741.

    Article  MATH  Google Scholar 

  • Geman, S., Geman, D., Graffigne, C. and Dong, P., Boundary detection by Constrained Optimization, IEEE Trans. Pattern Anal, and Mach. Int. 12 (1990).

    Google Scholar 

  • Grayson, M., The heat equation shrinks embedded plane curves to round points, J. Diff. Geom. 26 (1987), 285–314.

    MathSciNet  MATH  Google Scholar 

  • Grenander, U., Lectures in Pattern Theory I, II and III: Pattern Analysis, Pattern Synthesis and Regular Structures, Springer-Verlag, Heidelberg-New York, 1976–1981.

    Google Scholar 

  • Grossberg, S. and Mingolla, E., Neural dynamics of form perception: boundary completion, illusory figures and neon color spreading, Psych. Rev. 92 (1985), 173–211.

    Article  Google Scholar 

  • Grossman, A. and Morlet, J., Decomposition of Hardy functions into square integrable wavelets of constant shape, SIAM J. Math. Anal. 15 (1984), 723–736.

    Article  Google Scholar 

  • Hertz, J., Krogh, A. and Palmer, R., Introduction to the Theory of Neural Computation, Addison-Wesley, 1991.

    Google Scholar 

  • Hildreth, E., The Measurement of Visual Motion, MIT Press, Cambridge, 1984.

    Google Scholar 

  • Hopfield, J., Neural Networks and Physical Systems with Emergent Collective Computational Abilities, in Proc. Nat. Acad. 79(1982), 2554–2558.

    Article  MathSciNet  Google Scholar 

  • Kass, M., Witkin, A. and Terzopoulos, D., Snakes: Active Contour Models, IEEE Proc. 1st Int. Conf. Computer Vision, 1987, 259–268.

    Google Scholar 

  • Kirkpatrick, S., Geloti, C. and Vecchi, M., Optimization by Simulated Annealing Science 220 (1983), 671–680.

    Google Scholar 

  • Lauritzen, S. and Spiegelhalter, D., Local Computations with Probabilities on Graphical Structures and their Applications to Expert Systems, J. Royal Stat. Soc. B 50 (1988), 157–224.

    MathSciNet  MATH  Google Scholar 

  • Leclerc, Y., Constructing simple stable descriptions for image partitioning, Int. J. Comp. Vision 3 (1989), 73–102.

    Article  Google Scholar 

  • Lee, T.S., Mumford, D. and Yuille, A., Texture Segmentation by Minimizing Vector-Valued Energy Functionals, in Proc. Eur. Conf. Comp. Vision, Springer Lecture Notes in Computer Science 1427 (1992).

    Google Scholar 

  • Mallat, S., A theory of multi-resolution signal decomposition: the wavelet representation, IEEE Trans. PAMI 11 (1989), 674–693.

    Article  MATH  Google Scholar 

  • Meyer, Y., Principe d’incertitude, bases hilbertiennes et algèbres d’opérateurs, Séminaire Bourbaki, Springer Lecture Notes in Math, Berlin-Heidelberg-New York, (1986).

    Google Scholar 

  • Mumford, D., Mathematical theories of shape: Do they model perception?, Proc. SPIE 1570 (1991), 2–10.

    Article  Google Scholar 

  • Mumford, D., On the computational architecture of the neocortex I and II, Biol. Cybernetics 65 (1991–92), 135–145 & 66, 241–251.

    Article  Google Scholar 

  • Mumford, D., Neuronal architectures for pattern-theoretic problems, in Proc. Idyllwild conference on large scale neuronal theories of the brain, C. Koche (éd.), MIT Press, Cambridge, 1994.

    Google Scholar 

  • Mumford, D. and Shah, J., Optional approximation by piecewise smooth functions and associated variational problems, Comm. Pure & Applied Math. 42 (1989), 577–685.

    Article  MathSciNet  MATH  Google Scholar 

  • Nitzberg, M. and Mumford, D., The 2.1 D sketch, in Proc. 3rd IEEE Int. Conf. Comp. Vision, 1990, 138–144.

    Google Scholar 

  • Osherson, D. and Weinstein, S., Formal Learning Theory, in Handbook of Cognitive Neuroscience M. Gazzaniga (ed.), Plenum Press, New York, 1984, 275–292.

    Google Scholar 

  • Pearl, J., Probabilistic Reasoning in Intelligent Systems, Morgan-Kaufman, 1988.

    Google Scholar 

  • Perona, P. and Malik, J., Scale-space and edge detection using anisotropic diffusion, IEEE Workshop on Computer Vision, Miami, 1987.

    Google Scholar 

  • Rissanen, J., Stochastic Complexity in Statistical Inquiry, World Scientific, Singapore, 1989.

    MATH  Google Scholar 

  • Rosch, E., Principles of Categorization, in Cognition and Categorization, E. Rosch and B. Lloyd (eds.), L. Erlbaum, 1978.

    Google Scholar 

  • Rosenfeld, A. and Thurston, M., Edge and curve detection for visual scene analysis, IEEE Trans, on Computers C-20 (1971), 562–569.

    Google Scholar 

  • Thompson, D’Arcy, On Growth and Form, Cambridge University Press, Cambridge, 1917.

    Google Scholar 

  • Uhr, L., Layered “recognition cone” networks that preprocess, classify and describe, IEEE Trans, on Computers C-21 (1972), 758–768.

    Google Scholar 

  • Yamamoto, K. and Rosenfeld, A., Recognition of Handprinted Kanji Characters by a Relaxation Method, in Proc. 6th Int. Conf. Pattern Recognition, 1982, 395–398.

    Google Scholar 

  • Yuille, A. and Grzywacz, N., A Mathematical Analysis of the Motion Coherence Theory, Int. J. Comp. Vision 3(1989), 155–175.

    Article  Google Scholar 

  • Yuille, A., Hallinan, P., and Cohen, D. Feature Extraction from Faces using Deformable Templates, Int. J. Comp. Vision 6 (1992).

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1994 Birkhäuser Verlag

About this chapter

Cite this chapter

Mumford, D. (1994). Pattern Theory: A Unifying Perspective. In: Joseph, A., Mignot, F., Murat, F., Prum, B., Rentschler, R. (eds) First European Congress of Mathematics . Progress in Mathematics, vol 3. Birkhäuser Basel. https://doi.org/10.1007/978-3-0348-9110-3_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-0348-9110-3_6

  • Publisher Name: Birkhäuser Basel

  • Print ISBN: 978-3-0348-9911-6

  • Online ISBN: 978-3-0348-9110-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics