Abstract
This paper presents a biologically motivated model for low and mid-level vision tasks and its interpretation in computer vision terms. Initially we briefly present the biologically plausible model of image segmentation developed by Stephen Grossberg and his collaborators during the last two decades, that has served as the backbone of many researchers’ work. Subsequently we describe a novel version of this model with a simpler architecture but superior performance to the original system using nonlinear recurrent neural dynamics. This model integrates multi-scale contour, surface and saliency information in an efficient way, and results in smooth surfaces and thin edge maps, without posterior edge thinning or some sophisticated thresholding process. When applied to both synthetic and true images it gives satisfactory results, favorably comparable to those of classical computer vision algorithms. Analogies between the functions performed by this system and commonly used techniques for low- and mid-level computer vision tasks are presented. Further, by interpreting the network as minimizing a cost functional, links with the variational approach to computer vision are established.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Adelson, E., Bergen, J.: Spatiotemporal energy models for the perception of motion. JOSA 2(2), 284–299 (1985)
Black, M., Sapiro, G., Marrimont, D., Heeger, D.: Robust anisotropic diffusion. IEEE Trans. on Image Processing 7(3), 421–432 (1998)
Carandini, M., Heeger, D.: Summation and division by neurons in visual cortex. Science 264, 1333–1336 (1994)
Canny, J.: A computational approach to edge detection. IEEE Trans. on PAMI 8(6), 679–698 (1986)
Cohen, M.A., Grossberg, S.: Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. on Systems, Man and Cybernetics 13(5), 815–826 (1983)
Daugman, J.: Uncertainty relation for resolution in space, spatial frequency and orientation optimized by two-dimensional visual cortical filters. JOSA 2(7), 160–169 (1985)
Deriche, R.: Using Canny’s criteria to derive a recursively implemented optimal edge detector. IJCV 1(2), 167–187 (1987)
Field, D., Hayes, A., Hess, R.: Contour integration by the human visual system: Evidence for a local ‘association field’. Vision Research 33(2), 173–193 (1993)
Geman, S., Geman, D.: Stochastic relaxation, Gibbs distributions, and the bayesian treatment of images. IEEE Trans. on PAMI 66(6), 721–741 (1984)
Grossberg, S.: Neural Networks and Natural Intelligence. MIT Press, Cambridge (1988)
Grossberg, S.: 3-d vision and figure-ground separation by visual cortex. Perception and Psychophysics 55, 48–121 (1994)
Grossberg, S., Mingolla, E.: Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations. Perc. & Psych.s 38, 141–171 (1985)
Grossberg, S., Mingolla, E.: Neural dynamics of surface perception: Boundary webs, illuminants, and shape from shading. CVGIP 37, 116–165 (1987)
Grossberg, S., Mingolla, E., Williamson, J.: Synthetic aperture radar processing by a multiple scale neural system for boundary and surface representation. Neural Networks 8(7-8), 1005–1028 (1995)
Guy, G., Medioni, G.: Inferring global perceptual contours from local features. IJCV 20(1), 113–133 (1996)
Heitger, F., von der Heydt, R.: A computational model of neural contour processing: Figure-ground segregation and illusory contours. In: Proc. ICCV, pp. 32–40 (1993)
Hopfield, J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. of the N.A.S. of USA 81, 3088–3092 (1984)
Koch, C., Marroquin, J., Yuille, A.: Analog neuronal networks in early vision. MIT AI lab Technical report 751 (1985)
Lee, T.S.: A bayesian framework for understanding texture segmentation in the primary visual cortex. Vision Research 35, 2643–2657 (1995)
Li, Z.: Visual segmentation by contextual influences via intracortical interactions in primary visual cortex. Network: Comput. Neur. Syst. 10, 187–212 (1999)
Mumford, D.: Elastica and computer vision. In: Bajaj, J. (ed.) Algebraic Geometry and its applications, pp. 507–518. Springer, Heidelberg (1993)
Neumann, H., Sepp, W.: Recurrent V1-V2 interaction in early visual boundary processing. Biological Cybernetics 91, 425–444 (1999)
Parent, P., Zucker, S.W.: Trace inference, curvature consistency, and curve detection. IEEE Trans. on PAMI 11(8), 823–839 (1989)
Perona, P., Malik, J.: Detecting and localizing edges composed of steps, peaks and roofs. In: Proc. ICCV, pp. 52–57 (December 1990)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. on PAMI 12(7), 629–639 (1990)
Sha’ashua, A., Ullman, S.: Structural saliency: the detection of globally salient structures using a locally connected network. In: Proc. ICCV, pp. 321–327 (1988)
Ren, X., Malik, J.: A probabilistic multi-scale model for contour completion based on image statistics. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 312–327. Springer, Heidelberg (2002)
Williams, L.R., Jacobs, D.W.: Stochastic completion fields: A neural model of illusory contour shape and salience. Neural Computation 9(4), 837–858 (1997)
Yuille, A.: Energy functions for early vision and analog networks. MIT A.I. lab technical report, 987 (1987)
Yuille, A., Geiger, D.: A common framework for image segmentation. IJCV 6, 227–243 (1991)
Kokkinos, R., Deriche, O.: Faugeras and P. Maragos Towards bridging the gap between biological and computational segmentation. INRIA Research Report (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kokkinos, I., Deriche, R., Maragos, P., Faugeras, O. (2004). A Biologically Motivated and Computationally Tractable Model of Low and Mid-Level Vision Tasks. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3022. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24671-8_40
Download citation
DOI: https://doi.org/10.1007/978-3-540-24671-8_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21983-5
Online ISBN: 978-3-540-24671-8
eBook Packages: Springer Book Archive