Abstract

We propose a technique to increase the robustness of a snake-based segmentation method originally introduced to track the shape of a target with random white Gaussian intensity upon a random white Gaussian background. Because these statistical conditions are not always fulfilled with optronic images, we describe two improvements that increase the field of application of this approach. We first show that regularized whitening preprocessing allows one to apply the original method successfully for a target with a correlated texture upon a correlated background. We then introduce a simple multiscale approach that increases the robustness of the segmentation against the initialization of the snake (i.e., the initial shape used for the segmentation). These results provide a robust and practical method for determination of the reference image for correlation techniques.

© 1998 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. A. VanderLugt, IEEE Trans. Inf. Theory IT-10, 139 (1964).
  2. B. V. K. Vijaya Kumar, Appl. Opt. 31, 4773 (1992).
    [CrossRef]
  3. O. Germain and Ph. Réfrégier, Opt. Lett. 21, 1845 (1996).
    [CrossRef] [PubMed]
  4. M. Kass, A. Witkin, and D. Terzopoulos, Int. J. Computer Vision 1, 321 (1988).
    [CrossRef]
  5. R. Ronfard, Int. J. Computer Vision 2, 229 (1994).
    [CrossRef]
  6. C. Kervrann and F. Heitz, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994) p. 724.
    [CrossRef]
  7. F. Goudail and Ph. Réfrégier, Opt. Lett. 21, 495 (1996).
    [CrossRef] [PubMed]
  8. F. Guérault and Ph. Réfrégier, Opt. Commun. 142, 197 (1997).
    [CrossRef]
  9. R. Deriche, Int. J. Computer Vision 1, 167 (1987).
    [CrossRef]

1997 (1)

F. Guérault and Ph. Réfrégier, Opt. Commun. 142, 197 (1997).
[CrossRef]

1996 (2)

1994 (1)

R. Ronfard, Int. J. Computer Vision 2, 229 (1994).
[CrossRef]

1992 (1)

1988 (1)

M. Kass, A. Witkin, and D. Terzopoulos, Int. J. Computer Vision 1, 321 (1988).
[CrossRef]

1987 (1)

R. Deriche, Int. J. Computer Vision 1, 167 (1987).
[CrossRef]

1964 (1)

A. VanderLugt, IEEE Trans. Inf. Theory IT-10, 139 (1964).

Deriche, R.

R. Deriche, Int. J. Computer Vision 1, 167 (1987).
[CrossRef]

Germain, O.

Goudail, F.

Guérault, F.

F. Guérault and Ph. Réfrégier, Opt. Commun. 142, 197 (1997).
[CrossRef]

Heitz, F.

C. Kervrann and F. Heitz, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994) p. 724.
[CrossRef]

Kass, M.

M. Kass, A. Witkin, and D. Terzopoulos, Int. J. Computer Vision 1, 321 (1988).
[CrossRef]

Kervrann, C.

C. Kervrann and F. Heitz, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994) p. 724.
[CrossRef]

Réfrégier, Ph.

Ronfard, R.

R. Ronfard, Int. J. Computer Vision 2, 229 (1994).
[CrossRef]

Terzopoulos, D.

M. Kass, A. Witkin, and D. Terzopoulos, Int. J. Computer Vision 1, 321 (1988).
[CrossRef]

VanderLugt, A.

A. VanderLugt, IEEE Trans. Inf. Theory IT-10, 139 (1964).

Vijaya Kumar, B. V. K.

Witkin, A.

M. Kass, A. Witkin, and D. Terzopoulos, Int. J. Computer Vision 1, 321 (1988).
[CrossRef]

Appl. Opt. (1)

IEEE Trans. Inf. Theory (1)

A. VanderLugt, IEEE Trans. Inf. Theory IT-10, 139 (1964).

Int. J. Computer Vision (3)

M. Kass, A. Witkin, and D. Terzopoulos, Int. J. Computer Vision 1, 321 (1988).
[CrossRef]

R. Ronfard, Int. J. Computer Vision 2, 229 (1994).
[CrossRef]

R. Deriche, Int. J. Computer Vision 1, 167 (1987).
[CrossRef]

Opt. Commun. (1)

F. Guérault and Ph. Réfrégier, Opt. Commun. 142, 197 (1997).
[CrossRef]

Opt. Lett. (2)

Other (1)

C. Kervrann and F. Heitz, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Institute of Electrical and Electronics Engineers, New York, 1994) p. 724.
[CrossRef]

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (3)

Fig. 1
Fig. 1

Scene with strongly correlated texture: (a) initialization of the snake, (b) final state of the snake after optimization of Jw, s upon image (a), (c) final state of the snake after optimization of Jw, s upon the preprocessed version image of (a).

Fig. 2
Fig. 2

Cross sections of the spectra of the background of (a) the input image and (b) preprocessed image. Histograms of the background of (c) the input image and (d) the preprocessed image.

Fig. 3
Fig. 3

Initialization of the snake at scales of (a) 1/4 (64×64 image), (b) 1/2 (128×128 image; this is the final state of the snake at a scale of 1/4); and (c) scale  1 (256×256 image; this is the final state of the snake at a scale of 1/2). (d) Final state of the snake on the input image.

Equations (4)

Equations on this page are rendered with MathJax. Learn more.

si=aiwi+bi1-wi.
Jw, s=Nawlogσ~a2w+Nbwlogσ~a2w,
m~uw=1NuwSusi, σ~u2w=1NuwSusi-m^uw2,
z^ν=s^νμ+s^ν,

Metrics