Multicut workflow for large connectomics data. Using luigi for pipelining and caching processing steps. Most of the computations are done out-of-core using hdf5 as backend and implementations from nifty
We propose to use a kernel density estimation (KDE) based approach for classification. This non-parametric approach intrinsically provides the likelihood of membership for each class in a principled manner. The implementation was used in Ghani2016. Any papers using this code should cite Ghani2016 accordingly. The software has been tested under Matlab R2013b.