Contour extraction by mixture density description obtained from region clustering

  • Minoru Etoh
  • Yoshiaki Shirai
  • Minoru Asada
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)


This paper describes a contour extraction scheme which refines a roughly estimated initial contour to outline a precise object boundary. In our approach, mixture density descriptions, which are parametric descriptions of decomposed sub-regions, are obtained from region clustering. Using these descriptions, likelihoods that a pixel belongs to the object and its background are evaluated. Unlike other active contour extraction schemes, region-and edge-based estimation schemes are integrated into an energy minimization process using log-likelihood functions based on the mixture density descriptions. Owing to the integration, the active contour locates itself precisely to the object boundary for complex background images. Moreover, C1 discontinuity of the contour is realized as changes of the object sub-regions' boundaries. The experiments show these advantages.


Active Contour Object Boundary Region Cluster Active Contour Model Mixture Density 
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.


  1. 1.
    Blake, A., Zisserman, A.: Visual Reconstruction. The MIT Press (1987)Google Scholar
  2. 2.
    Mumford, D., Shah, J.: Boundary Detection by Minimizing Functionals. Proc. CVPR'85 (1985) 22–26Google Scholar
  3. 3.
    Kass, M., Witikin, A., Terzopoulos, D.: SNAKES: Active Contour Models. Proc. 1st ICCV (1987)259–268Google Scholar
  4. 4.
    Menet, S., Saint-Marc, P., Mendioni, G.: B-snakes: Implementation and Application to Stereo. Proc. DARPA Image Understanding Workshop '90 (1990) 720–726Google Scholar
  5. 5.
    Cohen, L., Cohen, I.: A Finite Element Method Applied to New Active Contour Models and 3D Reconstruction from Cross Sections. Proc. 3rd ICCV (1990) 587–591Google Scholar
  6. 6.
    Berger, M., Mohr, R.: Towards Autonomy in Active Contour Models. Proc. 11th ICPR (1990) 847–851Google Scholar
  7. 7.
    Dennis, J., Schnabel, R.: Numerical Methods for Unconstrained Optimization and Linear Equations. Prentice-Hall (1988)Google Scholar
  8. 8.
    Duda, R., Hart, P.: Pattern Classification and Scene Analysis. John Wiley and Sons (1973)Google Scholar
  9. 9.
    Scolve, S.: Application of the Conditional Population-Mixture Model to Image Segmentation. IEEE Trans. on Patt. Anal. & Mach. Intell. 5 (1983) 429–433Google Scholar
  10. 10.
    Yarman-Vural, F.: Noise, Histogram and Cluster Validity for Gaussian-Mixtured Data. Pattern Recognition 20 (1987) 385–501Google Scholar
  11. 11.
    Izumi, N., Morikawa, H., Harashima, H.: Combining Color and Spatial Information for Segmentation. IEICE 1991 Spring Nat. Convention Record, Part 7 (1991) 392 (in Japanese)Google Scholar
  12. 12.
    Crisman, J., Thorpe, C.: UNSCARF, A Color Vision System for the Detection of Unstructured Roads. Proc. Proc. Int. Conf. on Robotics & Auto. (1991) 2496–2501Google Scholar
  13. 13.
    Jain, A., Dubes, R.: Algorithms for Clustering Data. Prentice-Hall (1988)Google Scholar
  14. 14.
    Carman, C., Merickel, M: Supervising ISODATA with an Information Theoretic Stopping Rule. Pattern Recognition 23 (1990) 185–197Google Scholar
  15. 15.
    Akaike, H.: A New Look at Statistical Model Identification. IEEE Trans. on Automat. Contr. 19 (1974) 716–723Google Scholar
  16. 16.
    Etoh, M., Shirai, Y., Asada, M.: Active Contour Extraction by Mixture Density Description Obtained from Region Clustering, SIGPRU Tech. Rep. 91–81. IEICE of Japan (1991)Google Scholar
  17. 17.
    Amini, A., Weymouth, T., Jain, R.: Using Dynamic Programming for Solving Variational Problems in Vision. IEEE Trans. on Patt. Anal. & Mach. Intell. 12 (1990) 855–867Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Minoru Etoh
    • 1
  • Yoshiaki Shirai
    • 2
  • Minoru Asada
    • 2
  1. 1.Central Research LaboratoriesMatsushita Electric Ind.OsakaJapan
  2. 2.Mech. Eng. for Computer-Controlled MachineryOsaka UniversityOsakaJapan

Personalised recommendations