[SciPy-user] fitting mixed gaussians

[David Cournapeau]

Emanuele Zattin wrote:
> Hello,
> i'm trying to perform mixed-gaussian fitting on some small greyscale
> images (5x5 pixels, maximum 9x9). right now i'm using a leastsq
> approach but it tends to get pretty slow and unreliable when it comes
> to fit 4-5 2D gaussians even in such a small domain.
> I've noticed PyEM and i have the feeling it might be useful for me,
> but here i'm dealing with pixel intensities, not distributions. Any
> hint is welcome!
>
>   
If I understand your problem well, you have one image and wants to fit 
one, possibly several Gaussian on it. pyem won't help you for that, or 
more exactly, would be both overkill and gives really poor performances 
(even for only one gaussian, if it is not centered, with a few tens 
samples, it would be pretty bad, I think).

David