Abstract
Early computer vision is dominated by image patches or features derived from them; high-level vision is dominated by shape representation and recognition. However there is almost no work between these two levels, which creates a problem when trying to recognize complex categories such as “airports” for which natural feature clusters are ineffective. In contrast, the neurobiology of vision indicates a very rich interaction between low- and high-level constructs, because there is a rich system of feedback connections. Based on this, we argue that an intermediate-level representation is necessary for computer vision and that it should incorporate certain high-level notions of distance and geometric arrangement into a form derivable from images. We propose an algorithm based on a reaction-diffusion equation that meets these criteria; we prove that it reveals (global) aspects of the distance map locally; and illustrate its performance on airport and other imagery, including visual illusions. Finally, we conjecture that these ideas also can inform the neurobiology of vision, by providing a novel basis for neural computation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ambrosio, L., Tortorelli, V.: On the approximation of functionals depending on jumps by elliptic functionals via? γ-convergence. Commun. Pure Appl. Math. 43(8), 999–1036 (1990)
Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 6(15), 1373–1396 (2003)
Ben-Shahar, O., Zucker, S.W.: Geometrical computations explain projection patterns of long-range horizontal connections in visual cortex. Neural Comput. 16(3), 445–4476 (2003)
Borenstein, E., Ullman, S.: Combined top-down/bottom-up segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 30(12), 2109–2125 (2008)
Coifman, R., Lafon, S., Lee, A., Maggioni, M., Nadler, B., Warner, F., Zucker, S.W.: Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps. Proc. Nat. Acad. Sci. USA 102, 7426–7431 (2005)
Courant, R., Hilbert, D.: Methods of Mathematical Physics, vol. 2. Interscience, New York (1962)
Craft, E., Schutze, H., Niebur, E., von der Heydt, R.: A neural model of figure-ground organization. J Neurophysiol. 97(6), 4310–4326 (2007)
Dimitrov, P., Zucker, S.W.: A constant production hypothesis that predicts the dynamics of leaf venation patterning. Proc. Nat. Acad. Sci. USA 13(24), 9363–9368 (2006)
Dimitrov, P., Zucker, S.W.: Distance maps and plant development #1: Uniform production and proportional destruction. arXiv.org, arXiv:0905.4446v1 (q-bio.QM), 1–39 (2009)
Dimitrov, P., Zucker, S.W.: Distance maps and plant development #2: Facilitated transport and uniform gradient. arXiv.org, arXiv:0905.4662v1 (q-bio.QM)(24), 1–46 (2009)
Dimitrov, P., Lawlor, M., Zucker, S.W.: Distance images and intermediate-level vision. In: Bruckstein, A.M., ter Haar Romeny, B.M., Bronstein, A.M., Bronstein, M.M. (eds.). Third International Conference on Scale Space and Variational Methods in Computer Vision. Lecture Notes in Computer Science, vol. 1, pp. 653664. Springer (2011)
Dubuc, B., Zucker, S.W.: Complexity, confusion, and perceptual grouping. part i: the curve like representation. Int. J. Comput. Vis. 42(1), 55–82 (2001)
Elder, J., Zucker, S.W.: Contour closure and the perception of shape. Vis. Res. 33(7), 981–991 (1993)
Ferrari, V., Jurie, F., Schmid, C.: From images to shape models for object detection. Int. J. Comput. Vis. 87(3), 284–303 (2010)
Fidler, S., Leonardis, A.: Towards scalable representations of object categories: learning a hierarchy of parts. In: Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 1823 June 2007, Minneapolis, MN IEEE Computer Society (2007)
Florack, L.M.J., ter Haar Romeny, B.M., Viergever, M.A., Koenderink, J.J.: The Gaussian scale-space paradigm and the multiscale local jet. Int. J. Comput. Vis. 18(1), 61–75 (1996)
Froyen, V., Feldman, J., Singh, M.: A bayesian framework for figure-ground interpretation. Adv. Neural Inf. Process. Syst. 23, 631–639 (2010).
Gregory, R.L.: Eye and Brain. McGraw Hill, New York (1966)
Hubel, D.H., Wiesel, T.N.: Functional architecture of macaque monkey visual cortex. Proc. R. Soc. Lond. B 198, 1–59 (1977)
Koenderink, J.J.: The structure of images. Biol. Cybern. 50, 363–370 (1984)
Koffka, K.: Principles of Gestalt Psychology. Harcourt, Brace & World, New York (1935)
Lamme, V.A.F.: The neurophysiology of figure ground segregation in primary visual cortex. J. Neurosci. 15, 1605–1615 (1995)
Lee, T.S., Mumford, D., Romeo, R., Lamme, V.A.F.: The role of the primary visual cortex in higher level vision. Vis. Res. 38, 2429–2454 (1998)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91–110 (2004)
McKeown, D.M., Harvey, W.A., McDermott, J.: Rule-based interpretation of aerial imagery. IEEE Trans. Pattern Anal. Mach. Intell. 7(5), 570–585 (1985)
Montemurro, M.A., Rasch, M.J., Murayama, Y., Logothetis, N.K., Panzeri, S.: Phase-of-firing coding of natural visual stimuli in primary visual cortex. Curr. Biol. 18(5), 375–380 (2008)
Opelt, A., Pinz, A., Zisserman, A.: A boundary-fragment-model for object detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV (2). Lecture Notes in Computer Science, vol. 3952, pp. 575–588. Springer, Berlin/Heidelberg (2006)
Opelt, A., Pinz, A., Zisserman, A.: Learning an alphabet of shape and appearance for multi-class object detection. Int. J. Comput. Vis. 80(1), 16–44 (2008)
Orban, G.A.: Higher order visual processing in macaque extrastriate cortex. Physiol. Rev. 88(1), 59–89 (2008)
Plonsey, R.: Bioelectric Phenomena. McGraw-Hill, New York (1969)
Qiu, F., von der Heydt, R.: Figure and ground in the visual cortex: V2 combines stereoscopic cues with gestalt rules. Neuron 47, 155–166 (2005)
Rubin, E.: Synsoplevede Figurer. Gyldendalske Boghandel, Nordisk Forlag, Denmark (1915)
Sajda, P., Finkel, L.: Intermediate-level visual representations and the construction of surface perception. J. Cognit. Neurosci. 7, 267–291 (1995)
Sakai, K., Nishimura, H.: Determination of border ownership based on the surround context of contrast. Neurocomputing 58, 843–848 (2004)
Siddiqi, K., Shokoufandeh, A., Dickinson, S.J., Zucker, S.W.: Shock graphs and shape matching. Int. J. Comput. Vis. 35(1), 13–32 (1999)
Tari, S., Genctav, M.: From a modified ambrosio-tortorelli to a randomized part hierarchy tree. In: Third International Conference on Scale Space and Variational Methods in Computer Vision, vol. 1. Springer, Berlin/Heidelberg (2011)
Treisman, A., Gelade, G.: A feature-integration theory of attention. Cognit. Psychol. 12(1), 97–136 (1980)
Ullman, S.: Visual routines. In: Fischler, M.A., Firschein, O. (eds.) Readings in Computer Vision: Issues, Problems, Principles, and Paradigms, pp. 298–328. Morgan Kaufmann, San Francisco (1987)
Ullman, S., Epshtein, B.: Visual classification by a hierarchy of extended fragments. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds.) Toward Category-Level Object Recognition. Lecture Notes in Computer Science, vol. 4170, pp. 321–344. Springer, Berlin/New York (2006)
Ward, L.M., Coren, S.: The effect of optically induced blur on the magnitude of the mueller-lyer illusion. Bull. Psychon. Soc. 7(5), 483–484 (1976)
Zhaoping, L.: Border ownership from intracortical interactions in visual area v2. Neuron 47, 143–153 (2005)
Zhou, H., Friedman, H.S., von der Heydt, R.: Coding of border ownership in monkey visual cortex. J. Neurosci. 20, 6594–6611 (2000)
Zipser, K., Lamme, V.A.F., Schiller, P.H.: Contextual modulation in primary visual cortex. J. Neurosci. 16(22), 7376–7389 (1996)
Zucker, S.W.: Local field potentials and border ownership: a conjecture about computation in visual cortex. J. Physiol. (Paris) 106, 297–315 (2012)
Acknowledgements
The computer vision content in this paper was in [11]; I thank P. Dimitrov and M. Lawlor for permission to reuse that material here. S. Tari pointed out the possible connection to Ambrosio-Tortorelli. Research supported by AFOSR, ARO, NIH/NIAAA and NSF.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Zucker, S.W. (2013). Distance Images and the Enclosure Field: Applications in Intermediate-Level Computer and Biological Vision. In: Breuß, M., Bruckstein, A., Maragos, P. (eds) Innovations for Shape Analysis. Mathematics and Visualization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34141-0_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-34141-0_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34140-3
Online ISBN: 978-3-642-34141-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)