Advertisement

International Journal of Computer Vision

, Volume 46, Issue 3, pp 201–221 | Cite as

Subjective Surfaces: A Geometric Model for Boundary Completion

  • A. Sarti
  • R. Malladi
  • J.A. Sethian
Article

Abstract

We present a geometric model and a computational method for segmentation of images with missing boundaries. In many situations, the human visual system fills in missing gaps in edges and boundaries, building and completing information that is not present. Boundary completion presents a considerable challenge in computer vision, since most algorithms attempt to exploit existing data. A large body of work concerns completion models, which postulate how to construct missing data; these models are often trained and specific to particular images. In this paper, we take the following, alternative perspective: we consider a given reference point within the image, and then develop an algorithm which tries to build missing information on the basis of the given point of view and the available information as boundary data to the algorithm. Starting from this point of view, a surface is constructed. It is then evolved with the mean curvature flow in the metric induced by the image until a piecewise constant solution is reached. We test the computational model on modal completion, amodal completion, and texture segmentation. We extend the geometric model and the algorithm to 3D in order to extract shapes from low signal/noise ratio ultrasound image volumes. Results in 3D echocardiography and 3D fetal echography are also presented.

subjective surfaces segmentation perceptual contours level sets differential geometry Riemannian geometry surface evolution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Caselles, V., Catte', F., Coll, T., and Dibos, F. 1993. A geometric model for active contours. Numerische Mathematik, 66:1–31.Google Scholar
  2. Caselles, V., Kimmel, R., and Sapiro, G. 1997a. Geodesic active contours. IJCV, 22(1):61–79.Google Scholar
  3. Caselles, V., Kimmel, R., Sapiro, G., and Sbert, C. 1997b. Minimal surfaces based object segmentation. IEEE Trans. PAMI, 19(4):394–398.Google Scholar
  4. Chan, T.F. and Vese, L.A. 1998. Active contours without edges. CAM Report 98-53, UCLA Dept. of Mathematics.Google Scholar
  5. DoCarmo, M.P. 1976. Differential Geometry of Curves and Surfaces. Prentice Hall: Englewood Cliffs, NJ.Google Scholar
  6. Gabor, D. 1946. Theory of communication. J. Inst. Elect. Eng., 93:429–457.Google Scholar
  7. Giaquinta, M. and Hildebrandt, S. 1996. Calculus of Variations I. Springer-Verlag: Berlin.Google Scholar
  8. Gregory, R.L. 1972. Cognitive contours. Nature, 238(5358):51–52.Google Scholar
  9. ter Haar Romeny, B.M. (Ed.). 1994. Geometry Driven Diffusion in Computer Vision. Kluwer: Dordrecht.Google Scholar
  10. Julesz, B. 1981. Textons, the elements of texture perception, and their interactions. Nature, 91(7):91–97.Google Scholar
  11. Kanizsa, G. 1976. Subjective contours. Scientific American,48–52.Google Scholar
  12. Kanizsa, G. 1979. Organization in Vision. Hardcover.Google Scholar
  13. Kanizsa, G. 1980. Grammatica del vedere Il. Mulino.Google Scholar
  14. Kass, M., Witkin, A., and Terzopoulos, D. 1988. Snakes: Active contours models. IJCV, 1(4):321–331.Google Scholar
  15. Kimmel, R., Malladi, R., and Sochen, N. 2000. Images as embedded maps and minimal surfaces: Movies, color, texture, and medical images. International Journal of Computer Vision, 39(2):111–129.Google Scholar
  16. Lee, T.S. 1996. Image representation using 2D Gabor-wavelets. IEEE Transaction on Pattern Analysis and Machine Intelligence, 18(10):959–971.Google Scholar
  17. LeVeque, R.J. 1992. Numerical Method for Conservation Laws. Birkhauser: Boston, MA.Google Scholar
  18. Malik, J., Belongie, S., Leung, T., and Shi, J. 2000. Contour and texture analysis for image segmentation. In Perceptual Organization for Artificial Vision Systems, K.L. Boyer and S. Sarkar (Eds.). Kluwer Academic: Dordrecht.Google Scholar
  19. Malik, J., Belongie, S., Shi, J., and Leung, T. 1999. Textons, contours and regions: Cue combination in image segmentation. Int. Conf. Computer Vision, Sept. 1999, Corfu, Greece.Google Scholar
  20. Malladi, R. and Sethian, J.A. 1996. Image processing: Flows under min/max curvature and mean curvature. Graphical Models and Image Processing, 38(2):127–141.Google Scholar
  21. Malladi, R. and Sethian, J.A. 1998. real-time algorithm for medical shape recovery. In Proceedings of ICCV'98, Mumbai, India, Jan. 1998, pp. 304–310.Google Scholar
  22. Malladi, R., Sethian, J.A., and Vemuri, B. 1993. Topology independent shape modeling scheme. SPIE Proceedings on Geometric Methods in Computer Vision II, San Diego, pp. 246–258.Google Scholar
  23. Malladi, R., Sethian, J.A., and Vemuri, B.C. 1995. Shape modeling with front propagation: A level set approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(2):158–175.Google Scholar
  24. Marr, D. 1982. Vision. W.H. Freeman & Co.: San Francisco.Google Scholar
  25. Mumford, D. 1994. Elastica and computer vision. In Algebraic Geometry and Its Applications, Chandrajit Bajaj (Ed.). Springer-Verlag: New York.Google Scholar
  26. Mumford, D. and Shah, J. 1989. Optimal approximations by piecewise smooth functions and associated variational problems. Communications on Pure and Applied Mathematics, XLII:577–685.Google Scholar
  27. Nishikawa, S. and Schoen, R. 1996. Geometric Variational Problems. Springer-Verlag: Tokyo.Google Scholar
  28. Osher, S. and Sethian, J.A. 1988. Front propagating with curvature dependent speed: Algorithms based on Hamilton Jacobi formulation. Journal of Computational Physics, 79:12–49.Google Scholar
  29. Perona, P. 1995. Deformable kernels for early vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(5):488–499.Google Scholar
  30. Perona, P. and Malik, J. 1987. Scale space and edge detection using anisotropic diffusion. In Proc. IEEE Computer Society Workshop on Computer Vision.Google Scholar
  31. Sarti, A. and Malladi, R. 2002. A geometric level set model for ultra-sound image analysis. LBNL-44442, Lawrence Berkeley National Laboratory, Oct. 1999; Geometric Methods in Bio-Medical Image Processing, R. Malladi (Ed.). Springer Verlag: New York.Google Scholar
  32. Sarti, A., Malladi, R., and Sethian, J.A. 2000. Subjective surfaces: A method for completion of missing boundaries. In the Proceedings of the National Academy of Sciences, 97(12):6258–6263.Google Scholar
  33. Sarti, A., Malladi, R., and Sethian, J.A. Elastic Subjective Surfaces, in preparation.Google Scholar
  34. Sarti, A., Mikula, K., and Sgallari, F. 1999. Nonlinear multiscale analysis of 3D echocardiographic sequences. IEEE Transactions on Medical Imaging, 18(6):453–466.Google Scholar
  35. Sarti, A., Ortiz, C., Lockett, S., and Malladi, R. 2000. A unified geometric model for 3D confocal image analysis in cytology. In IEEE Transactions on Biomedical Engineering, 47(12):1600–1609.Google Scholar
  36. Saund, E. 1999. Perceptual organization of occluding contours generated by opaque surfaces. CVPR.Google Scholar
  37. Sethian, J.A. 1985. Curvature and the evolution of fronts. Comm. Math. Phys., 101:487–499.Google Scholar
  38. Sethian, J.A. 1987. Numerical methods for propagating fronts. In Variational Methods for Free Surface Interfaces, P. Concus and R. Finn (Eds.). Springer-Verlag: New York.Google Scholar
  39. Sethian, J.A. 1999. Level Set Methods and Fast Marching Methods. Cambridge University Press: Cambridge.Google Scholar
  40. Sochen, N., Kimmel, R., and Malladi, R. 1998. A general framework for lowlevel vision. IEEE Transactions on Image Processing, 7(3).Google Scholar
  41. Williams, L.R. and Jacobs, D.W. 1997a. Stochastic completion fields: A neural model of illusory contour shape and salience. Neural Computation, 9(4):837–858.Google Scholar
  42. Williams, L.R. and Jacobs, D.W. 1997b. Local parallel computation of stochastic completion fields. Neural Computation, 9(4):859–881.Google Scholar

Copyright information

© Kluwer Academic Publishers 2002

Authors and Affiliations

  • A. Sarti
    • 1
  • R. Malladi
    • 2
  • J.A. Sethian
    • 2
  1. 1.DEIS, University of BolognaItaly
  2. 2.Department of Mathematics, Lawrence Berkeley National LaboratoryUniversity of CaliforniaBerkeleyUSA

Personalised recommendations