Learning-based segmentation for connectomics. ... Custom software tools that can cope with the large data volumes common in the field of connectomics are a prerequisite for the implementation and evaluation of novel segmentation techniques. Chapter 3 presents version 1.0 of ilastik, a joint effort of multiple researchers. I have co-written its volume viewing component, volumina. ilastik provides an interactive pixel classification work ow on largerthan-RAM datasets as well as a semi-automated segmentation module useful for acquiring gold standard segmentations. Furthermore, I describe new software for dealing with hierarchies of cell complexes as well as for blockwise image processing operations on large datasets.

References in zbMATH (referenced in 1 article )

Showing result 1 of 1.
Sorted by year (citations)

  1. Kröger, Thorben: Learning-based segmentation for connectomics (2014)