Abstract
This paper reviews a biologically-inspired geometric model for the functional circuits of the visual front-end. An axiomatic approach is taken towards the filters and their tasks in early vision. A high-dimensional Lie-group based approach models the convolutions of the receptive fields in a multi-scale, multi-orientation, multi-velocity, multi-spatial frequency, multi-disparity and multi-color framework. In these new, and essentially invertible, extra-dimensional expansions new geometric reasoning can be developed. They give a feasible approach to the understanding of context, Gestalt, and association fields and enable full exploitation of adaptive, geometry-driven strategies, such as for contour completion and convection. The high-dimensionality leads to high computational costs, but, just as in human vision, this can be solved by massively parallel implementations, which is one of the goals of the EU Human brain project.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See for most Mathematica code of the formulas in this chapter the book: [16].
References
Alexander, D., van Leeuwen, C.: Mapping of contextual modulation in the population response of primary visual cortex. Cogn. Neurodyn. 4, 124 (2012)
Bartfeld, E., Grinvald, A.: Relationships between orientation-preference pinwheels, cytochrome oxidase blobs, and ocular-dominance columns in primate striate cortex. Proc. Nat. Acad. Sci. U.S.A. 89(24), 11905–11909 (1992)
Bekkers, E.J., Duits, R., ter Haar Romeny, B.M., Berendschot, T.J.: A new retinal vessel tracking method based on orientation scores. arXiv:1212.3530v4, Computer Vision and Pattern Recognition, pp. 1–28 (2012)
Bergholm, F.: Edge focusing. IEEE Trans. Pattern Anal. Mach. Intell. 9, 726–741 (1987)
Citti, A., Sarti, G.: A cortical based model of perceptual completion in the roto-translation space. JMIV 24(3), 307–326 (2006)
Crair, M.C., Ruthazer, E.S., Gillespie, D.C., Stryker, M.P.: Relationship between the ocular dominance and orientation maps in visual cortex of monocularly deprived cats. Neuron 19, 307–318 (1997)
Duits, R., Felsberg, M., Granlund, G., ter Haar Romeny, B.: Image analysis and reconstruction using a wavelet transform constructed from a reducible representation of the Euclidean motion group. Int. J. Comput. Vis. 72(1), 79–102 (2007)
Duits, R., Franken, E.: Left-invariant diffusions on the space of positions and orientations and their application to crossing-preserving smoothing of HARDI images. Int. J. Comput. Vis., 40 (2010)
Duits, R., Franken, E.M.: Left invariant parabolic evolution equations on SE(2) and contour enhancement via invertible orientation scores, Part I: Linear left-invariant diffusion equations on SE(2). Q. Appl. Math. AMS 68, 255–292 (2010)
Duits, R., Franken, E.M.: Left invariant parabolic evolution equations on SE(2) and contour enhancement via invertible orientation scores, Part II: Nonlinear left-invariant diffusion equations on invertible orientation scores. Q. Appl. Math. AMS 68, 293–331 (2010)
Field, D., Hayes, A., Hess, R.F.: Contour integration by the human visual system: evidence for a local ‘association field’. Vis. Res. 33–2, 173–193 (1993)
Florack, L.M.J., ter Haar Romeny, B.M., Koenderink, J.J., Viergever, M.A.: Scale and the differential structure of images. Image Vis. Comput. 10(6), 376–388 (1992)
Frostig, R.D.: In vivo optical imaging of brain function. CRC Press, Boca Raton (2009)
Grinvald, A.: Imaging input and output dynamics of neocortical networks in vivo: exciting times ahead. Proc. Nat. Acad. Sci. U.S.A. 102(40), 14125–14126 (2005)
ter Haar Romeny, B.M. (ed.): Geometry-Driven Diffusion in Computer Vision. Computational Imaging and Vision Series, vol. 1. Kluwer Academic Publishers, Dordrecht (1994)
ter Haar Romeny, B.M. (ed.): Front-End Vision and Multi-Scale Image Analysis: Multi-Scale Computer Vision Theory and Applications, written in Mathematica. Computational Imaging and Vision Series, vol. 27. Springer, Berlin (2003)
Hadamard, J.: Sur les problèmes aux dérivées partielles et leur signification physique. Bul. Univ. Princeton 13, 49–62 (1902)
Hubel, D.H.: Eye, Brain and Vision. Scientific American Library, vol. 22. Scientific American Press, New York (1988)
Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J. Physiol. 160, 106–154 (1962)
Kaiser, D.: Physics and Feynman’s diagrams. Am. Sci. 93, 156–165 (2005)
Koenderink, J.J.: The structure of images. Biol. Cybern. 50, 363–370 (1984)
Lindeberg, T.: Scale-Space Theory in Computer Vision. The Kluwer International Series in Engineering and Computer Science. Kluwer Academic Publishers, Dordrecht (1994)
Lindeberg, T.: Image matching using generalized scale-space interest points. In: Kuijper, A., Bredies, K., Pock, T., Bischof, H. (eds.) ssvm 2013. LNCS, vol. 7893, pp. 355–367. Springer, Heidelberg (2013)
Misner, C.W., Thorne, K.S., Wheeler, J.A.: Gravitation. Freeman, San Francisco (1973)
Mooser, F., Bosking, W.H., Fitzpatrick, D.: A morphological basis for orientation tuning in primary visual cortex. Nature Neurosci. 7, 872–879 (2004)
Nielsen, M.: From paradigm to algorithms in computer vision. Master’s thesis, Department of Computer Science, University of Copenhagen, March 1995
Ohki, K., Chung, S., Chng, Y.H., Kara, P., Reid, R.C.: Functional imaging with cellular resolution reveals precise micro-architecture in visual cortex. Nature 433, 597–603 (2005)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12(7), 629–639 (1990)
Petitot, J.: Neurogéometrie de la vision-Modeles mathématiques et physiques des architectures fonctionelles. Les Éditions de l’École Polytechnique (2008)
Crandall, D.J., Huttenlocher, D.P.: Weakly supervised learning of part-based spatial models for visual object recognition. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 16–29. Springer, Heidelberg (2006)
Riggs, L.A., Ratliff, F.: The effects of counteracting the normal movements of the eye. J. Opt. Soc. Am. 42, 872–873 (1952)
Rodieck, R.W.: The First Steps in Seeing. Sinauer Associates Inc, Sunderland (1998)
Schwartz, L.: Théorie des Distributions. Publications de l’Institut Mathématique de l’Université de Strasbourg, Paris (1950–1951)
Shmuel, A., Grinvald, A.: Coexistence of linear zones and pinwheels within orientation maps in cat visual cortex. Proc. Nat. Acad. Sci. 97(10), 5568–5573 (2000)
Swindale, N.V., Matsubara, J.A., Cynader, M.S.: Surface organization of orientation and direction selectivity in cat area 18. J. Neurosci. 7, 1414–1427 (1987)
ter Haar Romeny, B.M.: The Differential Structure of Images, pp. 565–582. CRC Press, Boca Raton (2012)
ter Haar Romeny, B.M.: Front-End Vision and Multi-scale Image Analysis. Springer Verlag, Berlin (2003)
Weickert, J.A.: Anisotropic diffusion in image processing. Ph.D. thesis, University of slautern, Department of Mathematics, Kaiserslautern, Germany, 29 January 1996
Weickert, J.A., Ishikawa, S., Imiya, A.: On the history of Gaussian scale-space axiomatics. In: Sporring, J., Nielsen, M., Florack, L.M.J., Johansen, P. (eds.) Gaussian Scale-Space Theory. Computational Imaging and Vision Series, Chap. 4, vol. 8, pp. 45–59. Kluwer Academic Publishers, Dordrecht (1997)
Weliky, M., Bosking, W.H., Fitzpatrick, D.: A systematic map of direction preference in primary visual cortex. Nature 379, 725–728 (1996)
Young, R.A.: The Gaussian derivative model for machine vision: visual cortex simulation. J. Opt. Soc. Am. (1986)
Young, R.A.: The Gaussian derivative model for machine vision: I. retinal mechanisms. Spat. Vis. 2(4), 273–293 (1987)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
ter Haar Romeny, B.M. (2014). A Geometric Model for the Functional Circuits of the Visual Front-End. In: Grandinetti, L., Lippert, T., Petkov, N. (eds) Brain-Inspired Computing. BrainComp 2013. Lecture Notes in Computer Science(), vol 8603. Springer, Cham. https://doi.org/10.1007/978-3-319-12084-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-12084-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12083-6
Online ISBN: 978-3-319-12084-3
eBook Packages: Computer ScienceComputer Science (R0)