Re: Accurate edge detection?

> 'Inverting' an uninvertible transform is not a new thing. This is more
> or less the definition of a so-called 'inverse problem'.
>
> illywhacker;

Course, you are right, and I do not pretend to discover here something
new. Only small enchancement. As I told before, the most interesting
fact is that nice result can be obtained using relatively simple
methods- linear algebra only. The non-linear op- set an appropriate
threshold and cut off all what is below (or above) it is too simple to
be spoken about