In function 'make_transformation_matrix', r=r*(pi/180) is used in 3D but not in 2D version. Why different representations are used in 2D/3D? Is it to compromise the scale difference between them?
One trivial thing I'd like to report is that:
in deciding max refinements steps (e.g., line 255 in 'register_image.m, Version18e'), its better to define the lower bound of MaxItt to account for small images.
An awesome library.
Dear Dirk, in file image_registration.m at line 533 to 543, shouldn't
come after computing filter size for Gaussian, i.e. after line 541
Since, O_trans is converted to vector, size(O_trans,2) is 1.
Thus, size(Istatic,2)/size(O_trans,2) = size(Istatic,2)
which is very large(around 130 for an image of size 400*530).