Method: SVM classify by z-pixel shadow

[JohnTigue]

This SVM tech is some simple stuff that should be checked out before going full on deep and convolutional. SVM is what was state-of-the-art a decade ago before deep learning stole the spotlight.

Identification of individual cells from z-stacks of bright-field microscopy images This

Really nice 2018 paper out of France. Simple, fast techniques (SVM classifier) simply looking at "z-pixels" (i.e. array of pixel intensities on the thin Z plane of a microscope slide; the colored curves). Basically, classifying SVM is light absorption around cell.

[JohnTigue]

This could be interesting. Say the SVM classifier can guess that something is in an area even if it cannot see it. If there is a break in a reconstruction, if the break endpoints are connected within a volume contiguously classified as probably containing something that might be a candidate for connecting the two endpoints.

[JohnTigue]

Instead of z-index use radius from line of SWC. I.e. walk vectors perpendicular to the SWC vectors. This is the path through the cell membrane which is a detector we want.