Robust Retrieval of 3D Structures from Image Stacks

Maria Garza-Jinich(1), Peter Meer(2) and Veronica Medina(3)

(1)Departamento de Ingenieria Electrica
Instituto de Investigaciones en Matematicas Aplicadas y en Sistemas
Universidad Nacional Autonoma de Mexico, Mexico D.F. 01000.

(2)Department of Electrical and Computer Engineering
Rutgers University, Piscataway, NJ 08855, USA.

(3)Departamento de Ingenieria Electrica
Universidad Autonoma Metropolitana, Iztapalapa, Mexico D.F. 09340.

Robust high breakdown point location estimators are employed to analyze image stacks under the piecewise constant image structure model. To reduce the effect of bias along the Z axis, the class parameters are extracted using three consecutive slices. The segmentation algorithm first determines the most reliable seed regions which are then used in a region-growing procedure supported by local evidence. The robustness and stability of the proposed technique is shown with both synthetic and real data, the latter consisting of one MRI and one confocal microscopy set. The performance of the algorithm is consistent with the ground truth obtained with manual segmentation by physicians.

Appeared in Medical Image Analysis, vol. 3, 21-35, 1999.
A shorter version appeared as, M. Garza-Jinich, P. Meer, V. Medina: Robust retrieval of 3D structures from magnetic resonance images. 13th International Conference on Pattern Recognition: Pattern Recognition and Signal Analysis. C: Applications and Robotics Systems. Vienna, Austria, August 1996, 391-395.
Return to Research: Robust analysis of visual data       Return to List of Publications
Download the paper