euclidean-distance-transform-3d
euclidean-distance-transform-3d copied to clipboard
seung-lab
Euclidean distance & signed distance transform for multi-label 3D anisotropic images using marching parabolas.
It would be nice to have anisotropy in all directions, not only along the axes. For n-dimensional image it could be parameterized by an n x n matrix defining the...
Currently, we increase the volume 8x in order to accommodate the voxel graph. For a 512x512x512 uint64 volume, this increases the memory usage. ```bash # Non-Voxel Graph 1 uint64 volume:...
In testing, it seems that about 69% of the time my test volume was bound by memory latency. This would seem to indicate that a cache aware version could be...
It's kind of presumptuous to occupy the prime PyPI real estate `edt` without supporting N-dimensions.
This would be importing a feature to binary processing that multi-label processing already has. For binary images that contain significant volumes of black pixels, we can skip processing the black...
I am curious if it would be possible to include the `return_indices` argument/ output of scipy.ndimage.distance_transform_edt, which returns a map of the closest object index for each pixel of the...
Hello, I tried to use edt after installation using pip (pip install edt). However, with the code below, I got a error message like this : TypeError: 'module' object is...
Hi! Numpy 2.0 is out, and recently I received the following error: ``` A module that was compiled using NumPy 1.x cannot be run in NumPy 2.0.0 as it may...
Thanks again for the great package! I've noticed that connected-components-3d is covered under LGPL. Is it possible to add LGPL to EDT? Thanks in advance!
