Research‎ > ‎

Image segmentation

We present a non-conformal metric that generalizes the geodesic active contours approach for image segmentation. The new metric is obtained by adding to the Euclidean metric an additional term that penalizes the misalignment of the curve with the image gradient and multiplying the resulting metric by a conformal factor that depends on the edge intensity. In this way, a closer fitting to the edge direction results. The provided experimental results address the computation of the geodesics of the new metric by applying a gradient descent to externally provided curves.


Contour extraction from MRI heart image.

References:
A. Valdés, J.I. Ronda, G. Gallego
Second-order Riemannian Active Contours for Image Segmentation
International Conference on Scientific Computation And Differential Equations (SciCADE), Sep. 16-20, 2013, Valladolid, Spain.
G. Gallego, J.I. Ronda, A. Valdés
Directional geodesic active contours
IEEE International Conference on Image Processing (ICIP) 2012, pp. 2561-2564. Sep. 30 - Oct 3, 2012. Orlando (FL), U.S.A.
doi,  Scopus,  PDF (OA-UPM)