A new methodology to automatically segment biomedical images
This paper presents a new approach for 2D object segmentations using an automatic method applied on images with severe noise conditions and locating objects with a very high degree of deformation. We use a physically-based shape model to obtain a deformable template, which is defined on a canonical ortogonal coordinate system. The proposed methodology works from a set of samples and from the output of an edge detector to segment the objects by using a reformulated Hough transform (automatic initialization) together with an optimization procedure (on a learned surface of deformation). Results from biomedical images are presented.
Key WordsDeformable template modal analysis Hough transform physically based modeling finite element method
Unable to display preview. Download preview PDF.
- 2.K. Bathe. Finite Element Procedures, Prentice-Hall, 1996.Google Scholar
- 3.J. Canny, A computational approach to edge detection, IEEE Trans. PAMI, vol. 8, n. 6, pp 679–698, 1986.Google Scholar
- 4.L. D. Cohen and I. Cohen, Finite-Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images, IEEE Trans. PAMI, vol. 15, no. 11, pp 1131–1147, 1993.Google Scholar
- 6.J. Illingworth, and J. Kittler, A Survey of the Hough transform, Comput. Vision, Graph & Image Process., Vol 44, pp 87–116, 1988.Google Scholar
- 7.F. Leymarie and M.D. Levine, Tracking Deformable Objects in the Plane Using and Active Contour Model, IEEE Trans. PAMI, vol. 15, N. 6, pp. 617–634, June 1993.Google Scholar
- 8.A. Pentland and S. Sclaroff. Closed-form solutions for physically-based shape modeling and recognition. IEEE Trans. PAMI, 13(7), pp. 715–729, July 1991.Google Scholar
- 9.T. Poggio and V. Torre, Ill-posed Problems and Regularization Analysis in Early Vision, Proc. of AARPA Image Understanding Workshop, pp. 257–263, 1984.Google Scholar
- 10.S. Sclaroff and A. Pentland. Modal Matching for Correspondence and Recognition, IEEE Trans. PAMI, vol 17, no. 6, pp 545–561, 1995.Google Scholar