Abstract
We match shapes, even under severe deformations, via a smooth re-parametrization of their integral invariant signatures. These robust signatures and correspondences are the foundation of a shape energy functional for variational image segmentation. Integral invariant shape templates do not require registration and allow for significant deformations of the contour, such as the articulation of the object’s parts. This enables generalization to multiple instances of a shape from a single template, instead of requiring several templates for searching or training. This paper motivates and presents the energy functional, derives the gradient descent direction to optimize the functional, and demonstrates the method, coupled with a data term, on real image data where the object’s parts are articulated.
UCRL-CONF-212393. This work was performed under the auspices of the U. S. Department of Energy by Univesity of California Lawrence Livermore National Laboratory under contract No. W-7405-Eng-48. Supported by NSF IIS-0208197, AFOSR F49620-03-1-0095, ONR N00014-03-1-0850.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kendall, D.G.: The diffusion of shape. Advances in Appl. Probability 9, 428–430 (1977)
Pitiot, A., Delingette, H., Toga, A., Thompson, P.: Learning Object Correspondences with the Observed Transport Shape Measure. In: Taylor, C.J., Noble, J.A. (eds.) IPMI 2003. LNCS, vol. 2732, pp. 25–37. Springer, Heidelberg (2003)
Manay, S., Hong, B., Yezzi, A., Soatto, S.: Integral invariant signatures. In: European Conf. Comp. Vis. (2004)
Manay, S., Hong, B., Cremers, D., Yezzi, A., Soatto, S.: Integral invariants and shape matching. Pat. Anal. and Mach. Intell (2005) (submitted)
Bookstein, F.: The Measurement of Biological Shape and Shape Change. Lect. Notes in Biomath., vol. 24. Springer, New York (1978)
Cootes, T.F., Taylor, C.J., Cooper, D.M., Graham, J.: Active shape models – their training and applications. Comp. Vision Image Underst. 61, 38–59 (1995)
Cremers, D., Osher, S., Soatto, S.: Kernel density estimation and instrinsic alignment for knowledge-driven segmentation: Teaching level sets to walk. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 36–44. Springer, Heidelberg (2004)
Dryden, I.L., Mardia, K.V.: Statistical Shape Analysis. Wiley, Chichester (1998)
Fréchet, M.: Les courbes aléatoires. Bull. Inst. Int’l Stat. 38, 499–504 (1961)
Klassen, E., Srivastava, A., Mio, W., Joshi, S.H.: Analysis of planar shapes using geodesic paths on shape spaces. Pat. Anal. and Mach. Intell. 26, 373–383 (2004)
Grenander, U.: Lectures in Pattern Theory. Springer, Berlin (1976)
Grenander, U., Chow, Y., Keenan, D.M.: Hands: A Pattern theoretic Study of Biological Shapes. Springer, New York (1991)
Trouvé, A.: Diffeomorphisms, groups, and pattern matching in image analysis. Int. J. Computer Vision 28, 213–221 (1998)
Younes, L.: Computable elastic distances between shapes. SIAM J. Appl. Math. 58, 565–586 (1998)
Basri, R., Costa, L., Geiger, D., Jacobs, D.: Determining the similarity of deformable shapes. Vision Research 38, 2365–2385 (1998)
Gdalyahu, Y., Weinshall, D.: Flexible syntactic matching of curves and its application to automatic hierarchical classication of silhouettes. Pat. Anal. and Mach. Intell. 21, 1312–1328 (1999)
Kass, M., Witkin, A., Terzopoulis, D.: Snakes: Active contour models. Int. J. Computer Vision 1, 321–323 (1987)
Kichenassamy, S., Kumar, A., Olver, P.J., Tannenbaum, A., Yezzi, A.: Analysis of planar shape influnce in geodesic active contours. In: Int. Conf. Comp. Vis., pp. 810–815 (1995)
Chan, T., Vese, L.: Active contours without edges. IEEE Trans. on Image Proc. 10, 266–277 (2001)
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. In: Int. Conf. Comp. Vis., pp. 694–699 (1995)
Tsai, A., Yezzi, A., Willsky, A.: Curve evolution implementation of the Mumford Shah functional for image segmentation, denoising, interpolation, and magnification. IEEE Trans. on Image Proc. 10, 1169–1186 (2001)
Leventon, M.E., Grimson, W.E.L., Faugeras, O.: Statistical shape influence in geodesic active contours. In: Proc. Conf. Comput. Vision and Pat. Rec., vol. 1, pp. 316–323 (2000)
Tsai, A., Yezzi, A., Wells, W., Tempany, C., Tucker, D., Fan, A., Grimson, E., Willsky, A.: Model-based curve evolution technique for image segmentation. In: Proc. Conf. Comput. Vision and Pat. Rec., pp. 463–468 (2001)
Chen, Y., Tagare, H., Thiruvenkadam, S., Huang, F., Wilson, D., Gopinath, K.S., Briggs, R.W., Geiser, E.: Using shape priors in geometric active contours in a variational framework. Int. J. Computer Vision 50, 315–328 (2002)
Rousson, M., Paragios, N.: Shape priors of level set represenations. In: European Conf. Comp. Vis., pp. 78–92 (2002)
Rousson, M., Paragios, N., Deriche, R.: Implicit active shape models for 3D segmentation in MRI imaging. In: Int. Conf. Medical Image Computing and Computer Assited Intervention, pp. 209–216 (2004)
Bakircioglu, M., Grenander, U., Khaneja, N., Miller, M.I.: Curve matching on brain surfaces using frenet distances. Human Brain Mapping 6, 329–333 (1998)
Sebastian, T., Klein, P., Kimia, B.: Alignment-based recognition of shape outlines. In: Arcelli, C., Cordella, L.P., Sanniti di Baja, G. (eds.) IWVF 2001. LNCS, vol. 2059, p. 606. Springer, Heidelberg (2001)
Tomasi, C., Manduchi, R.: Stereo without search. In: European Conf. Comp. Vis., pp. 452–465 (1996)
Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Comm. on Pure and Applied Math. 42 (1989)
Zhu, S.C., Yuille, A.: Region competition: Unifying snakes, region growing, and Bayes/MDL for multiband image segmentation. Pat. Anal. and Mach. Intell. 18, 884–900 (1996)
Nain, D., Yezzi, A., Turk, G.: Vessel segmentation using a shape driven flow. In: Int. Conf. Medical Image Computing and Computer Assited Intervention (2004)
Osher, S., Sethian, J.: Fronts propagating with curvature dependent speed: Algorithms based on Hamilton-Jacobi formulations. J. of Comp. Physics 79, 12–49 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Manay, S., Cremers, D., Yezzi, A., Soatto, S. (2005). One-Shot Integral Invariant Shape Priors for Variational Segmentation. In: Rangarajan, A., Vemuri, B., Yuille, A.L. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2005. Lecture Notes in Computer Science, vol 3757. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11585978_27
Download citation
DOI: https://doi.org/10.1007/11585978_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-30287-2
Online ISBN: 978-3-540-32098-2
eBook Packages: Computer ScienceComputer Science (R0)