So I've been experimenting with different Gaussian kernels within the Canny Edge detector. One thing that's jumped out at me, is I can't seem to reproduce the kernel that's listed here:
https://docs.opencv.org/2.4/doc/tutorials/imgproc/imgtrans/canny_detector/canny_detector.html#theory
nor here:
https://en.wikipedia.org/wiki/Canny_edge_detector#Gaussian_filter
My question: how did this particular kernel matrix have these particular values, and lines up with the generic formula?
Cause when I plug in a few indexes, the results don't match.
Thanks for your advice, Charles.