Abstract
Families of kernels that are useful in a variety of early vision algorithms may be obtained by rotating and scaling in a continuum a ‘template’ kernel. These multi-scale multi-orientation family may be approximated by linear interpolation of a discrete finite set of appropriate ‘basis’ kernels. A scheme for generating such a basis together with the appropriate interpolation weights is described. Unlike previous schemes by Perona, and Simoncelli et al. it is guaranteed to generate the most parsimonious one. Additionally, it is shown how to exploit two symmetries in edge-detection kernels for reducing storage and computational costs and generating simultaneously endstop- and junction-tuned filters for free.
This work was partially conducted while at MIT-LIDS with the Center for Intelligent Control Systems sponsored by ARO grant DAAL 03-86-K-0171.
Chapter PDF
Similar content being viewed by others
Keywords
- Singular Value Decomposition
- Edge Detection
- Discrete Fourier Transform
- Compact Operator
- Illusory Contour
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., and Bergen, J. Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. 2, 2 (1985), 284–299.
Adelson, E., and Bergen, J. Computational models of visual processing. M. Landy and J. Movshon eds. MIT press, 1991, ch. “The plenoptic function and the elements of early vision”. Also appeared as MIT-MediaLab-TR148. September 1990.
Binford, T. Inferring surfaces from images. Artificial Intelligence 17 (1981), 205–244.
Bovik, A., Clark, M., and Geisler, W. Multichannel texture analysis using localized spatial filters. IEEE trans. Pattern Anal. Mach. Intell. 12, 1 (1990), 55–73.
Burt, P., and Adelson, E. The laplacian algorithm as a compact image code. IEEE Transactions on Communications 31 (1983), 532–540.
Canny, J. A computational approach to edge detection. IEEE trans. Pattern Anal. Mach. Intell. 8 (1986), 679–698.
Choquet, G.Lectures on analysis, vol. I. W. A. Benjamin Inc., New York, 1969.
Dieudonne, J.Foundations of modern analysis. Academic Press, New York, 1969.
E. Simoncelli, W. Freeman, E. A., and Heeger, D. Shiftable multi-scale transforms. Tech. Rep. 161, MIT-Media Lab, 1991.
Fogel, I., and Sagi, D. Gabor filters as texture discriminators. Biol. Cybern. 61 (1989), 103–113.
Freeman, W., and Adelson, E. Steerable filters for early vision, image analysis and wavelet decomposition. In Third International Conference on Computer Vision (1990), IEEE Computer Society, pp. 406–415.
Freeman, W., and Adelson, E. The design and use of steerable filters for image analysis, enhancement and multi-scale representation. IEEE trans. Pattern Anal. Mach. Intell. (1991).
Freeman, W., and Adelson, E. Junction detection and classification. Invest. Ophtalmol. Vis. Sci. (Supplement) 32, 4 (1991), 1279.
Granlund, G. H. In search of a general picture processing operator. Computer Graphics and Image Processing 8 (1978), 155–173.
Heeger, D. Optical flow from spatiotemporal filters. In Proceedings of the First International Conference on Computer Vision (1987), pp. 181–190.
Heitger, F., Rosenthaler, L., von der Heydt, R., Peterhans, E., and Kübler, O. Simulation of neural contour mechanismn: From single to end-stopped cells. Tech. Rep. 126, IKT/Image science lab ETH-Zuerich, 1991.
Horn, B. The binford-horn linefinder. Tech. rep., MIT AI Lab. Memo 285, 1971.
Hubel, D., and Wiesel, T. Receptive fields of single neurones in the cat's striate cortex. J. Physiol. (Lond.) 148 (1959), 574–591.
Hubel, D., and Wiesel, T. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex. J. Physiol. (Lond.) 160 (1962), 106–154.
Jones, D., and Malik, J. Computational stereopsis-beyond zero-crossings. Invest. Ophtalmol, Vis. Sci. (Supplement) 31, 4 (1990), 529.
Jones, D., and Malik, J. Using orientation and spatial frequency disparities to recover 3d surface shape —a computational model. Invest. Ophtalmol. Vis. Sci. (Supplement) 32, 4 (1991), 710.
Kass, M. Computing visual correspondence. In Proceedings: Image Understanding Workshop (McLean, Virginia, June 1983), Science Applications, Inc, pp. 54–60.
Knuttson, H., and Granlund, G. H. Texture analysis using two-dimensional quadrature filters. In Workshop on Computer Architecture for Pattern Analysis ans Image Database Management (1983), IEEE Computer Society, pp. 206–213.
Koenderink, J., and Van Doorn, A. Representation of local geometry in the visual system. Biol Cybern. 55 (1987), 367–375.
Malik, J., and Gigus, Z. A model for curvilinear segregation. Invest. Ophtalmol. Vis. Sci. (Supplement) 32, 4 (1991), 715.
Malik, J., and Perona, P. Preattentive texture discrimination with early vision mechanisms. Journal of the Optical Society of America —A 7, 5 (1990), 923–932.
Morrone, M., and Burr, D. Feature detection in human vision: a phase dependent energy model. Proc. R. Soc. Lond. B 235 (1988), 221–245.
Morrone, M., and Burr, D. Robots and biological systems. Academic Press, eds. P. Dario and G. Sandini, 1990, ch.: “A model of human feature detection based on matched filters”.
Morrone, M., Burr, D., Ross, J., and Owens, R. Mach bands depend on spatial phase. Nature, 324 (1986), 250–253.
Morrone, M., and Owens, R. Feature detection from local energy. Pattern Recognition Letters 6 (1987), 303–313.
Parent, P., and Zucker, S. Trace inference, curvature consistency, and curve detection. IEEE trans. Pattern Anal. Mach. Intell. 11, 8 (1989), 823–839.
Perona, P. Finite representation of deformable functions. Tech. Rep. 90-034, International Computer Science Institute, 1947 Center st., Berkeley CA 94704, 1990.
Perona, P. Deformable kernels for early vision. IEEE Conference on Computer Vision and Pattern Recognition (June 1991), 222–227.
Perona, P. Deformable kernels for early vision. Tech. Rep. 2039, LIDS-MIT, October 1991. Submitted to IEEE PAMI.
Perona, P., and Malik, J. Detecting and localizing edges composed of steps, peaks and roofs. Tech. Rep. UCB/CSD 90/590, Computer Science Division (EECS), U.C.Berkeley, 1990.
Perona, P., and Malik, J. Detecting and localizing edges composed of steps, peaks and roofs. In Proceedings of the Third International Conference of Computer Vision (Osaka, 1990), IEEE Computer Society, pp. 52–57.
Pinkus, A. n-Widths in Approximation Theory. Springer Verlag, 1985.
Press, W., Flannery, B., Teukolsky, S., and Vetterling, W. Numerical Recipes in C. Cambridge University Press, 1988.
Rosenthaler, L., Heitger, F., Von Der Heydt, R., and Kübler, O. Detecting general edges and keypoints. Tech. Rep. 130, IKT/Image science lab ETH-Zuerich, 1991.
Turner, M. Texture discrimination by gabor functions. Biol. Cybern. 55 (1986), 71–82.
Zhong, S., and Mallat, S. Compact image representation from multiscale edges. In Proceedings of the Third International Conference of Computer Vision (Osaka, 1990), IEEE Computer Society.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Perona, P. (1992). Steerable-scalable kernels for edge detection and junction analysis. In: Sandini, G. (eds) Computer Vision — ECCV'92. ECCV 1992. Lecture Notes in Computer Science, vol 588. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55426-2_1
Download citation
DOI: https://doi.org/10.1007/3-540-55426-2_1
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55426-4
Online ISBN: 978-3-540-47069-4
eBook Packages: Springer Book Archive