Macro Problem Fit.doFit("Gaussian", X, Y)

[LIM Soon Yew John (IMB)]

Dear All,

After I update from ImageJ 1.47d to 1.47f, I get a poor curve fitting with the macro command "Fit.doFit("Gaussian", X, Y)". This problem occurs when the image has a low background. I had attached an example image and the macro below.

Y=getProfile();
len=Y.length;
X=newArray(len);
for(i=0;i<len;i++){
 X[i]=i;
}
Fit.doFit("Gaussian", X, Y);
Fit.plot;

Best Regards,
John
--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html

[LIM Soon Yew John (IMB)]

Dear All,

The problem with the curve fitting Fit.doFit("Gaussian", X, Y) will always happen when you used a longer line as shown in the macros below:

makeLine(100, 150, 200, 150);
Y=getProfile();
len=Y.length;
X=newArray(len);
for(i=0;i<len;i++){
 X[i]=i;
}
Fit.doFit("Gaussian", X, Y);
Fit.plot;

The curve fitting for the macro Fit.doFit("Gaussian",X,Y) works fine when the line is short but it fails when I used a longer line.

Best Regards,
John

________________________________________
From: ImageJ Interest Group [[hidden email]] On Behalf Of LIM Soon Yew John (IMB) [[hidden email]]
Sent: Tuesday, November 20, 2012 9:35 PM
To: [hidden email]
Subject: Macro Problem Fit.doFit("Gaussian", X, Y)

Dear All,

After I update from ImageJ 1.47d to 1.47f, I get a poor curve fitting with the macro command "Fit.doFit("Gaussian", X, Y)". This problem occurs when the image has a low background. I had attached an example image and the macro below.

Y=getProfile();
len=Y.length;
X=newArray(len);
for(i=0;i<len;i++){
 X[i]=i;
}
Fit.doFit("Gaussian", X, Y);
Fit.plot;

Best Regards,
John
--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html
--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html

[Michael Schmid]

Hi John,

oh, I see. Sorry, maybe I introduced a bug in the starting values. I'll try to get it fixed.

Michael
________________________________________________________________
On Nov 20, 2012, at 15:20, LIM Soon Yew John (IMB) wrote:

> Dear All,
>
> The problem with the curve fitting Fit.doFit("Gaussian", X, Y) will always happen when you used a longer line as shown in the macros below:
>
> makeLine(100, 150, 200, 150);
> Y=getProfile();
> len=Y.length;
> X=newArray(len);
> for(i=0;i<len;i++){
> X[i]=i;
> }
> Fit.doFit("Gaussian", X, Y);
> Fit.plot;
>
> The curve fitting for the macro Fit.doFit("Gaussian",X,Y) works fine when the line is short but it fails when I used a longer line.
>
> Best Regards,
> John
>
> ________________________________________
> From: ImageJ Interest Group [[hidden email]] On Behalf Of LIM Soon Yew John (IMB) [[hidden email]]
> Sent: Tuesday, November 20, 2012 9:35 PM
> To: [hidden email]
> Subject: Macro Problem Fit.doFit("Gaussian", X, Y)
>
> Dear All,
>
> After I update from ImageJ 1.47d to 1.47f, I get a poor curve fitting with the macro command "Fit.doFit("Gaussian", X, Y)". This problem occurs when the image has a low background. I had attached an example image and the macro below.
>
> Y=getProfile();
> len=Y.length;
> X=newArray(len);
> for(i=0;i<len;i++){
> X[i]=i;
> }
> Fit.doFit("Gaussian", X, Y);
> Fit.plot;
>
> Best Regards,
> John

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html

[Rasband, Wayne (NIH/NIMH) [E]]

On Nov 20, 2012, at 8:35 AM, LIM Soon Yew John (IMB) wrote:

> Dear All,
>
> After I update from ImageJ 1.47d to 1.47f, I get a poor curve fitting with the macro command "Fit.doFit("Gaussian", X, Y)". This problem occurs when the image has a low background. I had attached an example image and the macro below.

Thanks to Michael Schmid, this v1.47e regression is fixed in the v1.47g daily build.

-wayne

> Y=getProfile();
> len=Y.length;
> X=newArray(len);
> for(i=0;i<len;i++){
> X[i]=i;
> }
> Fit.doFit("Gaussian", X, Y);
> Fit.plot;
>
> Best Regards,
> John
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
> <lowBG.tif>

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html