search

HuXiaoling / TopoLoss

Code for the NeurIPS 2019 paper: Topology-Preserving Deep Image Segmentation
MIT License
155 stars 24 forks source link

Boundary mask of CREMI dataset #20

Closed wlsdzyzl closed 2 years ago

wlsdzyzl commented 2 years ago

Hello, how did you get the boundary mask of CREMI dataset? It only provides the neuron_ids. I can extract the boundareis by applying skimage.segmentation.find_boundarys on neuron_ids. But I got boundaries which seem thinner than what you have shown in paper. Did you add something such as a Gaussian blur? Thanks!

HuXiaoling commented 2 years ago

Yes, you are right that we can use the functions such as skimage.segmentation.find_boundarys to obtain the boundaries. Also, we use dilation/erosion operations (depending on whether the boundary is 1 or 0) to increase the thickness of the boundaries.

wlsdzyzl commented 2 years ago

Thanks!