An open-source toolkit to calculate geodesic distance for 2D and 3D images
GeodisTK: Geodesic Distance Transform Toolkit for 2D and 3D Images
Geodesic transformation of images can be implementated with two approaches: fast marching and raster scan. Fast marching is based on the iterative propagation of a pixel front with velocity F . Raster scan is based on kernel operations that are sequentially applied over the image in multiple passes . In GeoS , the authors proposed to use a 3x3 kernel for forward and backward passes for efficient geodesic distance transform, which was used for image segmentation.
Raster scan for geodesic distance transform. Image from .
DeepIGeoS  proposed to combine geodesic distance transforms with convolutional neural networks for efficient interactive segmentation of 2D and 3D images.
-  Sethian, James A. "Fast marching methods." SIAM review 41, no. 2 (1999): 199-235.
-  Borgefors, Gunilla. "Distance transformations in digital images." CVPR, 1986
-  Toivanen, Pekka J. "New geodesic distance transforms for gray-scale images." Pattern Recognition Letters 17, no. 5 (1996): 437-450.
-  Criminisi, Antonio, Toby Sharp, and Andrew Blake. "Geos: Geodesic image segmentation." ECCV, 2008.
-  Wang, Guotai, et al. "DeepIGeoS: A deep interactive geodesic framework for medical image segmentation." TPAMI, 2018. https://ieeexplore.ieee.org/document/8370732
A comparison of fast marching and ranster scan for 2D geodesic distance transform. (d) shows the Euclidean distance and (e) is a mixture of Geodesic and Euclidean distance.
This toolkit provides a cpp implementation of fast marching and raster scan for 2D/3D geodesic and Euclidean distance transforms and a mixture of them, and proivdes a python interface to use it. This is part of the work of DeepIGeoS . If you use our code, please cite this paper. https://ieeexplore.ieee.org/document/8370732
How to install
1, Install this toolkit easily by typing
pip install GeodisTK
2, Alternatively, if you want to build from source files, download this package and run
python setup.py build to
build the cpp files, then run
python setup.py install to install the package to default python path.
How to use
1, see a 2D example, run
2, see a 3D example, run
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size GeodisTK-0.1.5.3.tar.gz (9.2 kB)||File type Source||Python version None||Upload date||Hashes View hashes|