We present a novel approach to fully automated reconstruction of tree structures in noisy 2D images. Unlike in earlier approaches, we explicitly handle crossovers and bifurcation points, and impose geometric
constraints while optimizing a global cost function. We use manually annotated retinal scans to evaluate our method and demonstrate
that it brings about a very substantial improvement.
Türetken, E. [et al.]. Reconstructing geometrically consistent tree structures from noisy images. "Lecture notes in computer science", Setembre 2010, núm. 6361, p. 291-299.