Abstract
Many computer and robot vision applications require multi-scale image analysis. Classically, this has been accomplished through the use of a linear scale-space, which is constructed by convolution of visual input with Gaussian kernels of varying size (scale). This has been shown to be equivalent to the solution of a linear diffusion equation on an infinite domain, as the Gaussian is the Green's function of such a system (Koenderink, 1984). Recently, much work has been focused on the use of a variable conductance function resulting in anisotropic diffusion described by a nonlinear partial differential equation (PDE). The use of anisotropic diffusion with a conductance coefficient which is a decreasing function of the gradient magnitude has been shown to enhance edges, while decreasing some types of noise (Perona and Malik, 1987). Unfortunately, the solution of the anisotropic diffusion equation requires the numerical integration of a nonlinear PDE which is a costly process when carried out on a uniform mesh such as a typical image. In this paper we show that the complex log transformation, variants of which are universally used in mammalian retino-cortical systems, allows the nonlinear diffusion equation to be integrated at exponentially enhanced rates due to the nonuniform mesh spacing inherent in the log domain. The enhanced integration rates, coupled with the intrinsic compression of the complex log transformation, yields a speed increase of between two and three orders of magnitude, providing a means of performing rapid image enhancement using anisotropic diffusion.
Similar content being viewed by others
References
Alvarez, L., Lion, P.-L., and Morel, J.-M. 1992. Image selective smoothing and edge detection by nonlinear diffusion. II. SIAM Journal of Numerical Analysis, 29(3):845-866.
Alvarez, L. and Mazorr, L. 1994. Signal and image restoration using shock filters and anisotropic diffusion. SIAM Journal of Numerical Analysis, 31(2):590-605.
Bonmassar, G. and Schwartz, E.L. 1994. Geometric invariance in space-variant vision systems: The exponential chirp transform. In Proc. of the Int. Conf. on Pattern Recognition, ICPR-12, pp. 204-207.
Bonmassar, G. and Schwartz, E. 1995. Space-variant fourier analysis: The exponential chirp transform. IEEE Transactions on Pattern Analysis and Machine Intelligence, submitted.
Bonmassar, G. and Schwartz, E. 1996a. Fourier analysis and cortical architectures: The exponential chirp transform. Real Time Imaging, in press.
Bonmassar, G. and Schwartz, E.L. 1996b. Lie groups, space-variant fourier analysis and the exponential chirp transform. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, pp. 492-498.
Burt, P. and Adelson, E.H. 1983. The Laplacian pyramid as a compact image code. IEEE Transactions on Communications, 9(4):532-540.
Campbell, F. and Green, D. 1965. Optical quality of the human eye. Journal of Physiology(London), 186:558-578.
Catte, F., Lions, P.-L., Morel, J.-M., and Coll, T. 1992. Image selective smoothing and edge detection by nonlinear diffusion. SIAM Journal of Numerical Analysis, 29(1):182-193.
Churchill, R.V. and Brown, J.W. 1984. Complex Variables and Applications. McGraw-Hill Book Company: New York.
Cohen, M.A. and Grossberg, S. 1984. Neural dynamics of brightness perception: Features, boundaries, diffusion, and resonance. Perception and Psychophysics, 36:428-456.
Cottet, G.-H. and Germain, L. 1993. Image processing through reaction combined with nonlinear diffusion. Mathematics of Computation, 61(204):659-673.
Dang, T., Olivier, J., and Maitre, H. 1994. An image segmentation technique based on edge preserving smoothing filter and anisotropic diffusion. In Proc. of the IEEE Southwest Symposium on Image Analysis and Interpretation, pp. 65-69.
Daniel, P.M. and Whitteridge, D. 1961. The representation of the visual field on the cerebral cortex in monkeys. Journal of Physiology, 159:203-221.
El-Fallah, A.I. and Ford, G.E. 1994. Nonlinear adaptive image filtering based on inhomogeneous diffusion and differential geometry. SPIE Image and Video Processing II, 2182:49-63.
Engquist, B., Lotstedt, P., and Sjogreen, B. 1989. Nonlinear filters for efficient shock computation. Mathematics of Computation, 52(186):509-537.
Fischl, B. and Schwartz, E.L. 1996. Learned adaptive nonlinear filtering for anisotropic diffusion approximation in image processing. In Int. Conf. on Pattern Recognition, Vienna, Austria.
Fischl, B. and Schwartz, E. 1997a. Learning an integral equation approximation to nonlinear anisotropic diffusion in image processing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(4):342-352.
Fischl, B. and Schwartz, E.L. 1997b. Fast adaptive alternatives to nonlinear diffusion in image enhancement: Green’s function approximators and nonlocal filters. In First International Conference on Scale-Space Theory in Computer Vision, Utrecht University, Utrecht, the Netherlands.
Fischl, B., Cohen, M.A., and Schwartz, E.L. 1997. The local structure of space-variant images. Neural Networks, 10(4):815.
Gerrits, H. and Vendrik, J. 1970. Simultaneous contrast, filling-in process and information processing in man’s visual system. Experimental Brain Research, 11:411-430.
Grossberg, S. and Mingolla, E. 1985. Neural dynamics of form perception: Boundary completion, illusory figures, and neon color spreading. Psychological Review, 92(2):173-211.
Grossberg, S. and Todorovic, D. 1988. Neural dynamics of 1-D and 2-D brightness perception: A unified model of classical and recent phenomena. Perception and Psychophysics, 43:241-277.
Haberman, R. 1987. Elementary Applied Partial Differential Equations. 2nd edition. Prentice-Hall, Inc.: Englewood Cliffs, NJ.
Hummel, A. 1986. Representations based on zero-crossings in scalespace. In Readings in Computer Vision: Issues, Problems, Principles and Paradigms, M. Fischler and O. Firschein (Eds.), Morgan Kaufmann: Los Angeles.
Illner, R. and Neunzert, H. 1993. Relative entropy maximization and directed diffusion equations. Mathematical Methods in the Applied Sciences, 17:545-554.
Kacur, J. and Mikula, K. 1995. Solution of nonlinear diffusion appearing in image smoothing and edge detection. Applied Numerical Mathematics, 50:47-59.
Koenderink, J. 1984. The structure of images. Biological Cybernetics, 50:363-370.
Lee, T.S. 1995. A bayesian framework for understanding texture segmentation in the primary visual cortex. Vision Research, 35(18):2643.
Li, X. and Chen, T. 1994. Nonlinear diffusion with multiple edginess thresholds. Pattern Recognition, 27(8):1029-1037.
Malladi, R. and Sethian, J.A. 1995. Image processing via level set curvature flow. In Proc. of the National Academy of Sciences, vol. 92, pp. 7046-7050.
Marr, D. and Hildreth, E. 1980. Theory of edge detection. In Proc. of the Royal Society of London, vol. B 207, pp. 187-217.
Merigan, W.H. and Katz, L.M. 1990. Spatial resolution across the macaque retina. Vision Research, 30(7):985-991.
Messner, R. and Szu, H. 1986. An image processing architecture for real time generation of scale and rotation invariant patterns. Computer Vision, Graphics and Image Processing, 31:50-66.
Nitzberg, M. and Shiota, T. 1992. Nonlinear image filtering with edge and corner enhancement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(8):826-833.
Nördstrom, N.K. 1990. Biased anisotropic diffusion: A unified regularization and diffusion approach to edge detection. Image and Vision Computing, 8(4):318-327.
Oram, M.W. and Perrett, D.I. 1992. Time course of neural responses discriminating different views of the face and head. Journal of Neurophysiology, 68(1):70-84.
Osher, S. and Rudin, L.I. 1990. Feature-oriented image enhancement using shock filters. SIAM Journal of Numerical Analysis, 27(4):919-940.
Pauwels, E.J., Proesmans, M., Gool, L.J.V., Moons, T., and Oosterlinck, A. 1993. Segmentation and image enhancement using coupled anisotropic diffusion. SPIE, 2094:836-847.
Perona, P. and Malik, J. 1987. Scale space and edge detection using anisotropic diffusion. In Proc. of the IEEE Computer Society Workshop on Computer Vision, Miami, FL, pp. 16-27.
Perona, P. and Malik, J. 1990. Scale-space and edge detection using anisotropic diffusion. IEEE Trans. on Pattern Analysis and Machine Intell., 12(7):629-639.
Perona, P., Shiota, T., and Malik, J. 1994. Anisotropic diffusion. In Geometry Driven Diffusion in Computer Vision, B.M.T.H. Romeny (Ed.), Kluwer, chap. 3, pp. 73-92.
Price, C.B., Wambacq, P., and Oosterlinck, A. 1990. Image enhancement and analysis with reaction-diffusion paradigm. IEE Proceedings, 137 Pt. I(3):136-145.
Rojer, A.S. and Schwartz, E.L. 1990. Design considerations for a space-variant visual sensor with complex-logarithmic geometry. In 10th Int. Conf. on Pattern Recognition, vol. 2, pp. 278-285.
Rojer, A.S. and Schwartz, E.L. 1992. Biological basis for spacevariant sensor design II: Implications for VLSI sensor design. In SPIE Program on Computer Vision and Intelligent Robots IX: Advances in Intelligent Machines.
Sandini, G. and Dario, P. 1989. Active vision based on space-variant sensing. In Int. Symp. on Robotics Research.
Sandini, G., Bosero, F., Bontino, F., and Ceccherini, A. 1989. The use of an anthropomorphic visual sensor for motion estimation and object tracking. In Proc. of OSA Optical Meeting on Image Understanding and Machine Vision.
Schenker, P., Cande, E., Wong, K., and Patternson, W. 1981. New sensor geometries for image processing: computer vision in the polar exponential grid. In Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, pp. 1144-1148.
Schwartz, E. 1994. Computational studies of the spatial architecture of primate visual cortex: Columns, maps, and protomaps. In PrimaryVisual Cortex in Primates, A. Peters, and K. Rocklund (Eds.), vol. 10 of Cerebral Cortex, chap. 9. Plenum Press: New York.
Schwartz, E.L. 1977. Spatial mapping in the primate sensory projection: Analytic structure and relevance to perception. Biological Cybernetics, 25:181-194.
Schwartz, E.L. 1980. Computational anatomy and functional architecture of striate cortex: A spatial mapping approach to perceptual coding. Vision Research, 20:645-669.
Shah, J. 1996. A common framework for curve evolution, segmentation and anisotropic diffusion. In Proc. IEEE Computer Soc. Conf. on Computer Vision and Pattern Recognition, San Francisco, CA, pp. 136-142.
Talbot, S.A. and Marshall,W.H. 1941. Physiological studies on neural mechanisms of visual localization and discrimination. American Journal of Ophthalmology, 24:1255-1263.
Thorpe, S.J. and Imbert, M. 1989. Biological constraints on connectionist models. In Connectionism in Perspective, R. Pfeifer, Z. Schreter, and F. Fogelman-Soulie (Eds.), Elsevier, Amsterdam, pp. 63-92.
Vogels, R. and Orban, G.A. 1991. Quantitative study of striate single unit responses in monkey performing an orientation task. Experimental Brain Research, 84:1-11.
Wässle, H., Grünert, U., Röhrenbeck, J., and Boycott, B.B. 1990. Retinal ganglion cell density and cortical magnification factor in the primate. Vision Research, 30(11):1897-1911.
Weiman, C. 1988. 3-D sensing with polar exponential sensory arrays. In SPIE Conf. on Digital and Optical Shape Representation and Pattern Recognition.
Wertheim, T. 1894. Uber die indirekte sehscharfe. Zeitschrift fur Psychologie und Physiologie der Sinnesorgane, 7:172-187.
Whitaker, R.T. 1993. Geometry-limited diffusion in the characterization of geometric patches in images. CVGIP: Image Understanding, 57(1):111-120.
Whitaker, R.T. and Pizer, S.M. 1991. A multi-scale approach to nonuniform diffusion. Computer Vision, Graphics and Image Processing, 57:99-110.
Williams, D. and Coletta, N. 1987. Cone spacing and the visual resolution limit. Journal of the Optical Society of America, 4:1514-1523
Witkin, A. 1983. Scale-space filtering. In Int. Joint Conf. on Artificial Intell, Karlsruhe, Germany, pp. 1019-1021.
Yamamoto, H., Yeshurun, Y., and Levine, M.D. 1996. An active foveated vision system: Attentional mechanisms and scan path convergence measures. Computer Vision and Image Understanding: CVIU, 63(1):50.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Fischl, B., Cohen, M.A. & Schwartz, E.L. Rapid Anisotropic Diffusion Using Space-Variant Vision. International Journal of Computer Vision 28, 199–212 (1998). https://doi.org/10.1023/A:1008043919667
Issue Date:
DOI: https://doi.org/10.1023/A:1008043919667