NONPARAMETRIC STATISTICAL LEVEL SET SNAKE BASED ON THE MINIMIZATION OF THE STOCHASTIC COMPLEXITY

P. Martin, Ph. Réfrégier, F. Galland, F. Guérault

2006

Abstract

In this paper, we focus on the segmentation of objects not necessarily simply connected using level set snakes and we present a nonparametric statistical approach based on the minimization of the stochastic complexity (Minimum Description Length principle). This approach allows one to get a criterion to optimize with no free parameter to be tuned by the user. We thus propose to estimate the probability law of the gray levels of the object and the background of the image with a step function whose order is automatically determinated. We show that coupling the probability law estimation and the segmentation steps leads to good results on various types of images. We illustrate the robustness of the proposed nonparametric statistical snake on different examples and we show on synthetic images that the segmentation results are equivalent to those obtained with a parametric statistical technique, although the technique is non parametric and without ad hoc parameter in the optimized criterion.

References

  1. Chesnaud, C., Réfrégier, P., and Boulet, V. (1999). Statistical region snake-based segmentation adapted to different physical noise models. IEEE Trans. Pattern Anal. and Machine Intell., 21(11):1145-1157.
  2. Cover, T. M. and Thomas, J. A. (1991). Elements of Information Theory. Wiley-interscience, New York.
  3. Figueiredo, M. and Leita˜o, J. (1992). Bayesian estimation of ventricular contours in angiographic images. IEEE Trans. Medical Imaging, 11.
  4. Figueiredo, M., Leita˜o, J., and Jain, A. K. (2000). Unsupervised contour representation and estimation using B-splines and a minimum description length criterion. IEEE Trans. Image Processing, 9:1075-1087.
  5. Germain, O. and Réfrégier, P. (1996). Optimal snake-based segmentation of a random luminance target on a spatially disjoint background. Opt. Lett., 21(22):1845- 1847.
  6. Goudail, F., Réfrégier, P., and Ruch, O. (2003). Definition of a signal-to-noise ratio for object segmentation using polygonal mdl-based statistical snakes. In Energy Minimization Methods in Computer Vision and Pattern Recognition, pages 373-388. Springer.
  7. Jain, A. K. (1989). Fundamentals of digital image processing. Prentice Hall information and system sciences serie, New Jersey.
  8. Jain, A. K., Zhong, Y., and Lakshmanan, S. (1996). Object matching using deformable template. IEEE Trans. Pattern Anal. and machine intell., 18:268-278.
  9. Kass, M., Witkin, A., and Terzopoulos, D. (1988). Snakes: Active contour models. International Journal of Computer Vision, 1:321-331.
  10. Kim, J., Fisher, J., Yezzi, A., Cetin, M., and Willsky, A. (2002). Nonparametric methods for image segmentation using information theory and curve evolution. In IEEE Int. Conf. on Image Processing, volume 3, pages 797-800. Rochester, N.Y.
  11. Leclerc, Y. (1989). Constructing simple stable descriptions for image partitionning. Computer Vision, 3:73-102.
  12. Martin, P., Réfrégier, P., Goudail, F., and Guérault, F. (2004). Influence of the noise model on level set active contour segmentation. IEEE Trans. Pattern Anal. and Machine Intell., 26:799-803.
  13. Parzen, E. (1962). On estimation of a probability density function and mode. Annals Mathematical Statistics, 33:1065-1076.
  14. Rissanen, J. (1989). Stochastic Complexity in Statistical Inquiry. World Scientific, Singapore.
  15. Ronfard, R. (1994). Region-based strategies for active contour models. International Journal of Computer Vision, 2(13):229-251.
  16. Ruch, O. and Réfrégier, P. (2001). Minimal-complexity segmentation with a polygonal snake adapted to different optical noise models. Opt. Lett., 26(13):977-979.
Download


Paper Citation


in Harvard Style

Martin P., Réfrégier P., Galland F. and Guérault F. (2006). NONPARAMETRIC STATISTICAL LEVEL SET SNAKE BASED ON THE MINIMIZATION OF THE STOCHASTIC COMPLEXITY . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, ISBN 972-8865-40-6, pages 463-467. DOI: 10.5220/0001363204630467


in Bibtex Style

@conference{visapp06,
author={P. Martin and Ph. Réfrégier and F. Galland and F. Guérault},
title={NONPARAMETRIC STATISTICAL LEVEL SET SNAKE BASED ON THE MINIMIZATION OF THE STOCHASTIC COMPLEXITY},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,},
year={2006},
pages={463-467},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001363204630467},
isbn={972-8865-40-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,
TI - NONPARAMETRIC STATISTICAL LEVEL SET SNAKE BASED ON THE MINIMIZATION OF THE STOCHASTIC COMPLEXITY
SN - 972-8865-40-6
AU - Martin P.
AU - Réfrégier P.
AU - Galland F.
AU - Guérault F.
PY - 2006
SP - 463
EP - 467
DO - 10.5220/0001363204630467