Abstract
Shapes are continuous objects, even when they are drawn on digital media or composed using finite number of elements. As such, they defy analytic approach; explicitization of their parts, hierarchies, skeletons, or even centroids is ill-posed. I describe a novel approach to perceptually organize shapes and explicate their features without being negligent of their continuous nature. The basic construct is an unusual phase field that can be conceived in a number of varying ways using varying mathematical machinery, so highlighting the field itself rather than how it is being computed. Connections among the field, Mumford-Shah and Tari-Shah-Pien models, and reaction-diffusion equation suggest that the field may bridge low-level and high-level visual processing.
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)
Aslan, C.: Disconnected skeletons for shape recognition. Master’s thesis, Department of Computer Engineering, Middle East Technical University (2005)
Aslan, C., Tari, S.: An axis-based representation for recognition. In: Proceedings of the ICCV, pp. 1339–1346. Springer, Berlin/New York (2005)
Aslan, C., Erdem, A., Erdem, E., Tari, S.: Disconnected skeleton: shape at its absolute scale. IEEE Trans. Pattern Anal. Mach. Intell. 30(12), 2188–2203 (2008)
Bai, X., Latecki, L., Liu, W.Y.: Skeleton pruning by contour partitioning with discrete curve evolution. IEEE Trans. Pattern Anal. Mach. Intell. 29, 449–462 (2007)
Bar, L., Sochen, N., Kiryati, N.: Image deblurring in the presence of impulsive noise. Int. J. Comput. Vis. 70(3), 279–298 (2006)
Barenholtz, E., Feldman, J.: Visual comparisons within and between object-parts: evidence for a single- part superiority effect. Vis. Res. 43, 1655–1666 (2003)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell. 24, 509–522 (2002)
Biederman, I.: Recognition-by-components: a theory of human image understanding. Psychol. Rev. 94(2), 115–117 (1987)
Blum, H.: Biological shape and visual science. J. Theor. Biol. 38, 205–287 (1973)
Braides, A.: Approximation of Free-Discontinuity Problems. Lecture Notes in Mathematics, vol. 1694. Springer, Berlin/New York (1998)
Brockett, R., Maragos, P.: Evolution equations for continuous–scale morphology. In: Proceedings of the ICASSP, vol. 3, pp. 125–128. IEEE, Piscataway (1992)
Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: Proceedings of the CVPR, pp. 60–65. IEEE Computer Society, Los Alamitos (2005)
Burbeck, C.A., Pizer, S.M.: Object representation by cores: identifying and representing primitive spatial regions. Vis. Res. 35, 1917–1930 (1995)
Cohen, E.H., Singh, M.: Geometric determinants of shape segmentation: tests using segment identification. Vis. Res. 47, 2825–2840 (2007)
de Winter, J., Wagemans, J.: Segmentation of object outlines into parts: a large-scale integrative study. Cognition 99, 275–325 (1999)
Edelman, S., Cutzu, F., Duvdevani-Bar, S.: Similarity to reference shapes as a basis for shape representation. In: Proceedings of the COGSCI, San Diego (1996)
Erdem, E., Tari, S.: Mumford-Shah regularizer with contextual feedback. JMIV 33, 67–84 (2009)
Feldman, J., Singh, M.: Bayesian estimation of the shape skeleton. PNAS 103(47), 18014–18019 (2006)
Genctav, M.: Matching global skeleton. Master’s thesis, Department of Computer Engineering, Middle East Technical University (2010)
Gonzalez, R., Woods, R.: Digital Image Processing, 2nd edn. Addison-Wesley Longman Publishing Co., Inc., Boston (2001)
Gorelick, L., Galun, M., Sharon, E., Basri, R., Brandt, A.: Shape representation and classification using the poisson equation. IEEE Trans. Pattern Anal. Mach. Intell. 28(12), 1991–2005 (2006)
Hofmann, D., Richards, W.: Parts of recognition. Cognition 18, 65–96 (1984)
Jung, M., Vese, L.: Nonlocal variational image deblurring models in the presence of gaussian or impulse noise. In: Proceedings of the SSVM, pp. 401–412. Springer, Berlin/New York (2009)
Kimia, B., Tannenbaum, A., Zucker, S.: Shapes, shocks, and deformations I: the components of two-dimensional shape and the reaction-diffusion space. Int. J. Comput. Vis. 15(3), 189–224 (1995)
Leyton, M.: A process-grammar for shape. Art. Intell. 34(2), 213–247 (1988)
Macrini, D., Dickinson, S., Fleet, D., Siddiqi, K.: Bone graphs: medial shape parsing and abstraction. Comput. Vis. Image Underst. 115, 1044–1061 (2011)
Maragos, P., Butt, M.A.: Curve evolution, differential morphology and distance transforms as applied to multiscale and eikonal problems. Fundam. Inf. 41, 91–129 (2000)
March, R., Dozio, M.: A variational method for the recovery of smooth boundaries. Image Vis. Comput. 15(9), 705–712 (1997)
Marr, D.: Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. W.H. Freeman, San Francisco (1982)
Meyer, F.: Topographic distance and watershed lines. Signal Process. 38, 113–125 (1994)
Mi, X., DeCarlo, D.: Separating parts from 2d shapes using relatability. In: Proceedings of the ICCV, pp. 1–8. IEEE Computer Society, Los Alamitos (2007)
Morel, J.-M., Solimini, S.: Variational Methods in Image Segmentation. Birkhäuser, Boston (1995)
Mumford, D.: Mathematical theories of shape: do they model perception? In: Proceedings of the SPIE, vol. 1570. SPIE, Bellingham (1991)
Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Commun. Pure Appl. Math. 42, 577–685 (1989)
Navon, D.: Forest before trees: the precedence of global features in visual perception. Cogn. Psychol. 9, 355–383 (1977)
Pasupathy, A., Connor, C.: Population coding of shape in area V4. Nat. Neurosci. 5(2), 1332–1338 (2002)
Patz, T., Preusser, T.: Ambrosio-Tortorelli segmentation of stochastic images. In: Proceedings of the ECCV, pp. 254–267. Springer, Berlin (2010)
Pien, H.H., Desai, M., Shah, J.: Segmentation of mr images using curve evolution and prior information. IJPRAI 11(8), 1233–1245 (1997)
Preußer, T., Droske, M., Garbe, C., Rumpf, M., Telea, A.: A phase field method for joint denoising, edge detection and motion estimation. SIAM J. Appl. Math. 68(3), 599–618 (2007)
Proesman, M., Pauwels, E., van Gool, L.: Coupled geometry-driven diffusion equations for low-level vision. In: Romeny, B. (ed.) Geometry Driven Diffusion in Computer Vision. Lecture Notes in Computer Science. Kluwer, Dordrecht/Boston (1994)
Rosenfeld, A., Pfaltz, J.L.: Distance functions on digital pictures. Pattern Recognit. 1, 33–61 (1968)
Serra, J.: Image Analysis and Mathematical Morphology. London Academic, Orlando (1982)
Shah, J.: Segmentation by nonlinear diffusion. In: Proceedings of the CVPR, pp. 202–207. IEEE Computer Society, Los Alamitos (1991)
Shah, J.: A common framework for curve evolution, segmentation and anisotropic diffusion. In: Proceedings of the CVPR, pp. 136–142 (1996)
Shah, J.: Riemannian drums, anisotropic curve evolution and segmentation. In: Proceedings of the Scale-Space, pp. 129–140. Springer, Berlin/New York (1999)
Shah, J.: Skeletons and segmentation of shapes. Technical report, Northeastern University. http://www.math.neu.edu/~shah/publications.html (2005)
Shah, J., Pien, H.H., Gauch, J.: Recovery of shapes of surfaces with discontinuities by fusion of shading and range data within a variational framework. IEEE Trans. Image Process. 5(8), 1243–1251 (1996)
Siddiqi, K., Tresness, K.J., Kimia, B.: Parts of visual form: ecological and psychophysical aspects. Perception 25, 399–424 (1996)
Stiny, G.: Shape: Talking about Seeing and Doing. MIT, Cambridge (2006)
Tari, S., Genctav, M.: From a modified Ambrosio-Tortorelli to a randomized part hierarchy tree. In: Bruckstein, A.M., ter Haar Romeny, B.M., Bronstein, A.M., Bronstein, M.M. (eds.) Scale Space and Variational Methods. Lecture Notes in Computer Science, vol. 6667, pp. 267–278. Springer, Berlin/Heidelberg (2011)
Tari, S., Shah, J.: Simultaneous segmentation of images and shapes. In: Proceedings of the SPIE, San Diego, vol. 3168, San Diego pp. 88–94 (1997)
Tari, S., Shah, J.: Local symmetries of shapes in arbitrary dimension. In: Proceedings of the ICCV, pp. 1123–1128. Narosa, New Delhi (1998)
Tari, S., Shah, J., Pien, H.: A computationally efficient shape analysis via level sets. In: Proceedings of the MMBIA, pp. 234–243. IEEE Computer Society, Los Alamitos (1996)
Tari, S., Shah, J., Pien, H.: Extraction of shape skeletons from grayscale images. CVIU 66(2), 133–146 (1997)
Teboul, S., Blanc-Féraud, L., Aubert, G., Barlaud, M.: Variational approach for edge preserving regularization using coupled PDE’s. IEEE Trans. Image. Process. 7, 387–397 (1998)
Xu, C., Liu, J., Tang, X.: 2d shape matching by contour flexibility. IEEE Trans. Pattern Anal. Mach. Intell. 31(1), 180–186 (2009)
Zeng, J.T., Lakaemper, R., Wei, X., Li, X.: 2d shape decomposition based on combined skeleton-boundary features. In: Proceedings of the Advances in Visual Computing, 4th International Symposium, ISVC, pp. 682–691. Springer, Berlin/New York (2008)
Acknowledgements
The author thanks to the Alexander von Humboldt Foundation for a generous financial support and extends her gratitude to Folkmar Bornemann, Sci. Comp. Dept. of Tech. Universität München for providing a wonderful sabbatical stay during which this work has been completed. She also thanks to anonymous reviewers and the editors, A. Bruckstein, M. Breuß and P. Maragos, for their meticulous editing.
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
Tari, S. (2013). Fluctuating Distance Fields, Parts, Three-Partite Skeletons. 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_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-34141-0_20
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)