Nonlinear Spectral Image Decomposition and its Application to SegmentationMS32

Reliable and automated segmentation of objects of different scales is a key problem in the field of medical imaging. Recently, new theory and algorithms for nonlinear eigenvalue problems via spectral decompositions have been developed and shown to result in promising segmentation results. In this talk, we compare different data-terms for TV-based segmentation and evaluate how informative the resulting spectral response function is. The analysis is supported by segmentation results of simulated and experimental cell data.

This presentation is part of Minisymposium “MS32 - Nonlinear Spectral Theory and Applications (part 1)
organized by: Aujol Jean-Francois (University of Bordeaux) , Gilboa Guy (Electrical Engineering Department, Technion) .

Zeune Leonie (University of Twente)