In this paper, we propose a new minimal path model for minimally interactive
retinal vessel centerline extraction. The main contribution lies at the
construction of a novel coherence-penalized Riemannian metric in a lifted
space, dependently of the local geometry of tubularity and an external
scalar-valued reference feature map...
The globally minimizing curves associated
to the proposed metric favour to pass through a set of retinal vessel segments
with low variations of the feature map, thus can avoid the short branches
combination problem and shortcut problem, commonly suffered by the existing
minimal path models in the application of retinal imaging. We validate our
model on a series of retinal vessel patches obtained from the DRIVE and IOSTAR
datasets, showing that our model indeed get promising results.