K M
Posts:
17
Registered:
4/26/12
|
|
Re: Intensity correction using least-squares non-linear approximation question
Posted:
Jul 5, 2012 6:42 AM
|
|
"Bruno Luong" <b.luong@fogale.findmycountry> wrote in message <jt3ol8$qij$1@newscl01ah.mathworks.com>...
> "K M" wrote in message <jt3m0n$i6o$1@newscl01ah.mathworks.com>...
>
> >
> > hist(fun(I)) is approximately hist(J) and thus does operate on the input space ?
>
> But if
> fun = @(c) a*c + b
> and
> count is the histogram values, then
>
> a*count + b is _not_ the histogram of the hist(fun)
>
> To compute hits(fun) you need apply fun on the *bin* then to interpolate to get the count.
>
> Bruno
Thank you for your comment.
However, I do not understand how applying fun on the bins of the histogram would help me find the coefficients of the transformation, such that the histogram of the new transformed image is matched to the reference J. Apologies if I am missing something very straightforward.
|
|
