Automatic optimal filament segmentation with sub-pixel accuracy using generalized linear models and B-spline level-sets

Xun Xiao, Veikko F. Geyer, Hugo Bowne-Anderson, Jonathon Howard, Ivo F. Sbalzarini

Abstract: Highlights•Filament segmentation is a recurrent task in light-microscopy image analysis.•We combine the advantages of level-set and curve-fitting methods in a new model.•We present an optimal solver algorithm for the model, implemented in Fiji/ImageJ.•We derive a lower bound of the error in general filament-segmentation problems.•We show that our method asymptotically reaches the bound.