The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.06 - June (2010 vol.32)
pp: 1072-1083
Lewis D. Griffin , University College London, London
Martin Lillholm , University College London, London
ABSTRACT
We consider the measurement of image structure using linear filters, in particular derivative-of-Gaussian (DtG) filters, which are an important model of V1 simple cells and widely used in computer vision, and whether such measurements can determine local image symmetry. We show that even a single linear filter can be sensitive to a symmetry, in the sense that specific responses of the filter can rule it out. We state and prove a necessary and sufficient, readily computable, criterion for filter symmetry-sensitivity. We use it to show that the six filters in a second order DtG family have patterns of joint sensitivity which are distinct for 12 different classes of symmetry. This rich symmetry-sensitivity adds to the properties that make DtG filters well-suited for probing local image structure, and provides a set of landmark responses suitable to be the foundation of a nonarbitrary system of feature categories.
INDEX TERMS
Group theory, invariance, pattern analysis
CITATION
Lewis D. Griffin, Martin Lillholm, "Symmetry Sensitivities of Derivative-of-Gaussian Filters", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.32, no. 6, pp. 1072-1083, June 2010, doi:10.1109/TPAMI.2009.91
REFERENCES
[1] L.D. Griffin, "The Second Order Local-Image-Structure Solid," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 8, pp. 1355-1366, Aug. 2007.
[2] R.A. Young and R.M. Lesperance, "The Gaussian Derivative Model for Spatial-Temporal Vision: II. Cortical Data," Spatial Vision, vol. 14, nos. 3/4, pp. 321-389, 2001.
[3] J. Weickert, S. Ishikawa, and A. Imiya, "On the History of Gaussian Scale-Space Axiomatics," Gaussian Scale-Space Theory, pp. 45-59, Kluwer, 1997.
[4] M.A. Georgeson, "From Filters to Features—Location, Orientation, Contrast and Blur," Higher-Order Processing in the Visual System, pp. 147-165, Wiley, 1994.
[5] J.J. Koenderink and A.J. van Doorn, "Representation of Local Geometry in the Visual-System," Biological Cybernetics, vol. 55, no. 6, pp. 367-375, 1987.
[6] J.J. Koenderink, "Operational Significance of Receptive-Field Assemblies," Biological Cybernetics, vol. 58, no. 3, pp. 163-171, 1988.
[7] J.J. Koenderink and A.J. van Doorn, "Receptive-Field Families," Biological Cybernetics, vol. 63, no. 4, pp. 291-297, 1990.
[8] J.J. Koenderink and A.J. van Doorn, "Generic Neighborhood Operators," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 6, pp. 597-605, June 1992.
[9] L. Debnath, "On Hermite Transforms," Mathematicki Vesnik, vol. 1, no. 16, pp. 285-292, 1964.
[10] L. Debnath, Integral Transforms and Their Applications. CRC Press, 1995.
[11] L.M.J. Florack et al., "Scale and the Differential Structure of Images," Image and Vision Computing, vol. 10, no. 6, pp. 376-388, 1992.
[12] L.D. Griffin, "Histograms of Infinitesimal Neighbourhoods," Scale Space and Morphology in Computer Vision, M. Kerckhove, ed., pp. 326-334, Springer, 2001.
[13] T. Lindeberg and B.M. ter Haar Romeny, "Linear Scale-Space Theory I: Basic Theory," Geometry-Driven Diffusion in Computer Vision, B.M. ter Haar Romeny, ed., pp. 1-38, Kluwer, 1994.
[14] B.M.T. Romeny et al., "Higher-Order Differential Structure of Images," Image and Vision Computing, vol. 12, no. 6, pp. 317-325, 1994.
[15] B.M. ter Haar Romeny, Front-End Vision and Multi-Scale Image Analysis. Kluwer, 2003.
[16] D. Marr, Vision. W.H. Freeman & Co., 1982.
[17] L.D. Griffin and M. Lillholm, "Hypotheses for Image Features, Icons and Textons," Int'l J. Computer Vision, vol. 71, no. 3, pp. 213-230, 2006.
[18] X.W. Liu and D.L. Wang, "A Spectral Histogram Model for Texton Modeling and Texture Discrimination," Vision Research, vol. 42, no. 23, pp. 2617-2634, 2002.
[19] S.-C. Zhu et al., "What Are Textons?" Int'l J. Computer Vision, vol. 62, no. 1, pp. 121-143, 2005.
[20] M. Varma and A. Zisserman, "A Statistical Approach to Texture Classification from Single Images," Int'l J. Computer Vision, vol. 62, nos. 1/2, pp. 61-81, 2005.
[21] L.D. Griffin, "Feature Classes for 1D, Second Order Structure Arise from the Maximum Likelihood Statistics of Natural Images," Network: Computation in Neural Systems, vol. 16, nos. 2/3, pp. 301-320, 2005.
[22] L.D. Griffin, M. Lillholm, and M. Nielsen, "Natural Image Profiles Are Most Likely to be Step Edges," Vision Research, vol. 44, no. 4, pp. 407-421, 2004.
[23] L.D. Griffin, "Local Image Structure, Metamerism, Norms, and Natural Image Statistics," Perception, vol. 31, no. 3, pp. 377-377, 2002.
[24] E. Tagliati and L.D. Griffin, "Features in Scale Space: Progress on the 2D Second Order Jet," Lecture Notes in Computer Science, M. Kerckhove, ed., pp. 51-62, Springer, 2001.
[25] J.J. Koenderink and A.J. van Doorn, "Receptive Field Assembly Specificity," J. Visual Comm. and Image Representation, vol. 3, no. 1, pp. 1-12, 1992.
[26] J.J. Koenderink, "What Is a Feature?" J. Intelligent Systems, vol. 3, no. 1, pp. 49-82, 1993.
[27] J.J. Koenderink and A.J. van Doorn, "Metamerism in Complete Sets of Image Operators," Advances in Image Understanding, pp. 113-129, Wiley-IEEE CS Press, 1996.
[28] J.J. Koenderink and A.J. van Doorn, "Local Image Operators and Iconic Structure," Algebraic Frames for the Perception-Action Cycle, G. Sommer and J.J. Koenderink, eds., pp. 66-93, Springer, 1997.
[29] E. Cassirer, "The Concept og Group and the Theory of Perception," Philosophy and Phenomenological Research, vol. 5, no. 1, pp. 1-36, 1944.
[30] F. Klein, "A Comparative Review of Recent Researches in Geometry," Bull. New York Math. Soc., vol. 2, pp. 215-249, translated by M.W. Haskell, 1892.
[31] D. Lewis, "Extrinsic Properties," Philosophical Studies, vol. 44, pp. 111-112, 1983.
[32] S.Y. Auyang, Mind in Everyday Life and Cognitive Sciences. MIT Press, 2000.
[33] D. Schattschneider, MC Escher: Visions of Symmetry. Plenum Press, 1990.
[34] J.J. Koenderink and A.J. van Doorn, "Image Processing Done Right," Proc. European Conf. Computer Vision, 2002.
[35] L. Bieberbach, "Über die Bewegungsgruppen der Euklidischen Raume I," Mathematische Annalen, vol. 70, p. 297, 1911.
[36] J.H. Conway et al., "On Three-Dimensional Space Groups," Contributions to Algebra and Geometry, vol. 42, no. 2, pp. 475-507, 2001.
[37] B. Grünbaum and G.C. Shephard, Tilings and Patterns. W.H. Freeman & Co., 1987.
[38] W.T. Holser, "Classification of Symmetry Groups," Acta Crystallographica, vol. 14, pp. 1236-1242, 1961.
[39] A.A. Loeb, Color and Symmetry. Robert E. Krieger, 1978.
[40] L.D. Griffin, "Symmetries of 1D Images," J. Math. Imaging and Vision, vol. 31, nos. 2/3, pp. 157-164, 2008.
[41] L.D. Griffin, "Symmetries of 2D Images: Cases without Periodic Translation," to be published in J. Math. Imaging and Vision.
[42] Y. Bonneh, D. Reisfeld, and Y. Yeshurun, "Quantification of Local Symmetry—Application to Texture-Discrimination," Spatial Vision, vol. 8, no. 4, pp. 515-530, 1994.
[43] M. Mellor and M. Brady, "A New Technique for Local Symmetry Estimation," Proc. Conf. Scale Space and PDE Methods in Computer Vision, pp. 38-49, 2005.
[44] R. Scognamillo et al., "A Feature-Based Model of Symmetry Detection," Proc. Royal Soc. of London Series B—Biological Sciences, vol. 270, no. 1525, pp. 1727-1733, 2003.
[45] M. Xu and D. Pycock, "Estimating True Symmetry in Scale-Space," Proc. 1998 IEEE Int'l Conf. Systems, Man, and Cybernetics, pp. 4620-4625, 1998.
[46] S.C. Zhu, "Embedding Gestalt Laws in Markov Random Fields," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 11, pp. 1170-1187, Nov. 1999.
[47] Y.X. Liu, R.T. Collins, and Y.H. Tsin, "A Computational Model for Periodic Pattern Perception Based on Frieze and Wallpaper Groups," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 3, pp. 354-371, Mar. 2004.
[48] S. Oka et al., "VEPs Elicited by Local Correlations and Global Symmetry: Characteristics and Interactions," Vision Research, vol. 47, no. 16, pp. 2212-2222, 2007.
[49] S. Sally and R. Gurnsey, "Symmetry Detection across the Visual Field," Spatial Vision, vol. 14, no. 2, pp. 217-234, 2001.
[50] S.C. Dakin and A.M. Herbert, "The Spatial Region of Integration for Visual Symmetry Detection," Proc. Royal Soc. of London Series B —Biological Sciences, vol. 265, no. 1397, pp. 659-664, 1998.
[51] G.C. Baylis and J. Driver, "Perception of Symmetry and Repetition within and across Visual Shapes: Part-Descriptions and Object-Based Attention," Visual Cognition, vol. 8, no. 2, pp. 163-196, 2001.
[52] D.M. Levi and J. Saarinen, "Perception of Mirror Symmetry in Amblyopic Vision," Vision Research, vol. 44, no. 21, pp. 2475-2482, 2004.
[53] S.J.M. Rainville and F.A.A. Kingdom, "The Functional Role of Oriented Spatial Filters in the Perception of Mirror Symmetry— Psychophysics and Modeling," Vision Research, vol. 40, no. 19, pp. 2621-2644, 2000.
[54] S. Mancini, S.L. Sally, and R. Gurnsey, "Detection of Symmetry and Anti-Symmetry," Vision Research, vol. 45, no. 16, pp. 2145-2160, 2005.
[55] S.C. Dakin and R.J. Watt, "Detection of Bilateral Symmetry Using Spatial Filters," Spatial Vision, vol. 8, no. 4, pp. 393-413, 1994.
[56] T.-J. Cham and R. Cipolla, "Symmetry Detection through Local Skewed Symmetries," Image and Vision Computing, vol. 13, no. 5, pp. 439-450, 1995.
[57] G. Marola and M. Schiaffino, "Using Local Symmetry for Detecting 2-Dimensional Objects," Proc. Int'l Conf. Signal Processing, pp. 699-702, 1990.
[58] M. Milgram, R. Belaroussi, and L. Prevost, "Multi-Stage Combination of Geometric and Colorimetric Detectors for Eyes Localization," Proc. Conf. Image Analysis and Processing, pp. 1010-1017, 2005.
[59] O. Hansen and J. Bigun, "Local Symmetry Modeling in Multidimensional Images," Pattern Recognition Letters, vol. 13, no. 4, pp. 253-262, 1992.
[60] K.G. Cho and S.M. Dunn, "Hierarchical Local Symmetries," Pattern Recognition Letters, vol. 12, no. 6, pp. 343-347, 1991.
[61] M. Brady and H. Asada, "Smoothed Local Symmetries and Their Implementation," Int'l J. Robotics Research, vol. 3, no. 3, pp. 36-61, 1984.
[62] V. Braitenberg, Vehicles. Experiments in Synthetic Psychology. MIT Press, 1984.
[63] D. Perrett, "Symmetry and Human Facial Attractiveness," Evolution and Human Behavior, vol. 20, no. 5, pp. 295-307, 1999.
[64] M. Park et al., "Performance Evaluation of State-of-the-Art Discrete Symmetry Detection Algorithms," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, 2008.
[65] Y. Liu et al., "Digital Papercutting," Proc. ACM SIGGRAPH, 2005.
[66] S.M. Pizer et al., "Object Shape before Boundary Shape: Scale-Space Medial Axes," J. Math. Imaging and Vision, vol. 4, pp. 303-313, 1994.
[67] G. Loy and J.O. Eklundh, "Detecting Symmetry and Symmetric Constellations of Features," Proc. European Conf. Computer Vision, pp. 508-521, 2006.
[68] V. Prasad and L. Davis, "Detecting Rotational Symmetries," Proc. Int'l Conf. Computer Vision, pp. 346-352, 2005.
[69] H. Blum, "Biological Shape and Visual Science (Part I)," J. Theoretical Biology, vol. 38, pp. 205-287, 1973.
[70] B.A. Olshausen and D.J. Field, "How Close Are We to Understanding V1?" Neural Computation, vol. 17, no. 8, pp. 1665-1699, 2005.
[71] W.T. Freeman and E.H. Adelson, "The Design and Use of Steerable Filters," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 9, pp. 891-906, Sept. 1991.
[72] J.J. Koenderink and A.J. van Doorn, "Surface Shape and Curvature Scales," Image and Vision Computing, vol. 10, no. 8, pp. 557-565, 1992.
[73] J.J. Koenderink and A.J. van Doorn, "Local Structure of Gaussian Texture," IEICE Trans. Information and Systems, vol. IE86D, no. 7, pp. 1165-1171, 2003.
[74] M. Lillholm and L.D. Griffin, "Statistics and Category Systems for the Shape Index Descriptor of Local Image," Image and Vision Computing, 2008.
[75] A. Weinstein, "Groupoids: Unifying Internal and External Symmetry," Notices of the Am. Math. Soc., vol. 43, no. 7, pp. 744-752, 1996.
17 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool