We address the segmentation of piecewise-smooth real-valued functions having values on a complete, connected, 2-manifold embedded in $\R^3$. The main idea is to consider the functions as a sum of a piecewise constant component and a smooth component and to spatially combine total variation and L2 regularizations. The formulation is based on the minimization of a Convex Non-Convex functional where an ad-hoc non-convex regularization term improves the treatment of the boundary of the segmented regions.

This is poster number 30 in Poster Session

Authors:

Martin Huska (University of Bologna)

Keywords:

computer graphics, image segmentation, images on manifold, manifold segmentation