Strings: Variational Deformable Models of Multivariate Continuous Boundary Features

@article{Ghebreab2003StringsVD,
  title={Strings: Variational Deformable Models of Multivariate Continuous Boundary Features},
  author={Sennay Ghebreab and Arnold W. M. Smeulders},
  journal={IEEE Trans. Pattern Anal. Mach. Intell.},
  year={2003},
  volume={25},
  pages={1399-1410}
}
We propose a new image segmentation technique called strings. A string is a variational deformable model that is learned from a collection of example objects rather than built from a priori analytical or geometrical knowledge. As opposed to existing approaches, an object boundary is represented by a one-dimensional multivariate curve in functional space, a feature function, rather than by a point in vector space. In the learning phase, feature functions are defined by extraction of multiple… CONTINUE READING

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 23 REFERENCES

Automatic Construction of 2D Shape Models

N. Duta, A. K. Jain, M. P. Dubuisson-Jolly
  • IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 5, pp. 433-446, May 2001.
  • 2001
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Active Shape Models-Their Training and Application

  • Computer Vision and Image Understanding
  • 1995
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Statistical shape influence in geodesic active contours

  • 5th IEEE EMBS International Summer School on Biomedical Imaging, 2002.
  • 2002
VIEW 1 EXCERPT

Similar Papers