You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This might be stupid question but why do we not include 1/(pie^1/2) in dKernel? As per my understanding as Gaussians are separable, derivatives of Gaussians are separable, so dKernel are respective zeroth, first and second derivative of Gaussians but I see that for some reason we dont include 1/(pie^1/2) in the prefix (where prefix is the term which we multiply to baseKernel. I am using these features to segment collagen fibres.
This might be stupid question but why do we not include 1/(pie^1/2) in dKernel? As per my understanding as Gaussians are separable, derivatives of Gaussians are separable, so dKernel are respective zeroth, first and second derivative of Gaussians but I see that for some reason we dont include 1/(pie^1/2) in the prefix (where prefix is the term which we multiply to baseKernel. I am using these features to segment collagen fibres.
https://github.com/GriffinLab/BIFs/blob/b737a5ab3d45c8bde8e52e0ed7c18bb02239a385/Matlab/DtGfiltersBank.m#L18C39-L18C49
Thanks in advance
The text was updated successfully, but these errors were encountered: