Re: [Fwd: Re: Smoothing Functions without distorting matrices' edges]

[Søren Hauberg]

søn, 24 09 2006 kl. 20:22 +0200, skrev Søren Hauberg:
> Sadly, anisodiff.m won't run as is. Gives me an error about
> toascii, or such, when it tries to 
> >> im=double(im);
> 
> I must have an old form of double.m
> 
> I'm running 
> octave-2.1.50a-inst.exe on Win98
> so will look through the code to see what I can change.
For what it's worth, the code runs out of the box on 2.9.8.


> Two things catch my eye, one 'stability' ?!!!
I haven't used Perona-Malik that much, but a lot of image processing
people recommends the algorithm. I think the algorithm is a special case
of non-linear diffusion, and that the algorithm should be stable.

>  and the other,
> 'iterations'  I'm trying to vectorize this smoothing to
> make it snappy.  Right now I already have a program that
> expands the matrix, iterates smoothing for the slope, then
> smooths using conv2, then shaves it back to original size
> and it only takes 0.6 seconds on 1200,120  
I forgot about that part of your problem. On my machine the Perona-Malik
operation takes about a second or two, so it doesn't seem to be the
solution to your problem -- sorry.

Søren