Open BWWwustl opened 2 months ago
Hi, the eigenvalues of the Hessian matrix at a voxel in an image describe the local geometric shape:
A tube is elongated in one direction while not in the other two. This can be similarly described using the eigenvalues, where one has low values, while the other two have higher values.
For a detailed explanation please look into the journal and conference papers mentioned in the code description (readme) text.
Hi. Thanks for sharing the code. It is amazing algorithm.
I am a little bit confused about why the tube-like or elongated structures will have two Higher eigenvalues and one eigenvalue nearly equal to zero? Which exactly these eigenvalues represent for? Thanks!