Crest lines extraction in volume 3D medical images: a multi-scale approach

  title={Crest lines extraction in volume 3D medical images: a multi-scale approach},
  author={Olivier Monga and Richard Lengagne and Rachid Deriche},
Recently, we have shown that the diierential properties of the surfaces represented by 3D volumic images can be recovered using their partial derivatives. For instance, the crest lines can be characterized by the rst, second and third partial derivatives of the grey level function I(x; y; z). In this paper, we show that : the computation of the partial derivatives of an image can be improved using recursive lters which approximate the Gaussian lter, a multi-scale approach solves many of the… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 15 extracted citations

Medical Image Computing and Computer-Assisted Intervention – MICCAI’99

Lecture Notes in Computer Science • 1999
View 10 Excerpts
Highly Influenced

Deformable registration of male pelvises in CT images

2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821) • 2004
View 1 Excerpt


Publications referenced by this paper.
Showing 1-10 of 24 references

Computer vision applied to 3d medical images : Results, trends and future challenges

Nicholas Ayache
INRIA Report research, • 1993
View 1 Excerpt

Faugeras . Using third order derivatives toextract ridge lines in 3 d images

Olivier Monga, Rachid Deriche, Gregoire Malandain
IEEE Conference on Vision and Pattern Recognition • 1992

Using third order derivatives to extract ridge lines in 3d images

Olivier Monga, Serge Benayoun, Olivier D. Faugeras
In IEEE Conference on Vision and Pattern Recognition, • 1992
View 10 Excerpts

Invariant third order properties of isophotes: T-junction detection

J. Koenderink B. Romeny, L. Florack
In Proc. 7th Scandinavien Conference on Image Analysis, • 1991

Similar Papers

Loading similar papers…