Semi-automatic neuron segmentation in electron microscopy images via sparse labeling
2013
We introduce a novel method for utilizing user input to sparsely label membranes in electron microscopy images. Using gridlines as guides, the user marks where the guides cross the membrane to generate a sparsely labeled image. We use a best path algorithm to connect each of the sparse membrane labels. The resulting segmentation has a significantly better Rand error than automatic methods while requiring as little as 2% of the image to be labeled.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
7
References
3
Citations
NaN
KQI