MathGroup Archive 2012

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: 2D Gaussian fit

  • To: mathgroup at smc.vnet.net
  • Subject: [mg126264] Re: 2D Gaussian fit
  • From: Szabolcs Horvát <szhorvat at gmail.com>
  • Date: Sat, 28 Apr 2012 05:23:03 -0400 (EDT)
  • Delivered-to: l-mathgroup@mail-archive0.wolfram.com
  • References: <jnb4m4$5ic$1@smc.vnet.net>

On 2012.04.26. 11:31, zhaol01 at gmail.com wrote:
 > How can I fit a spot on an image to a 2D Gaussian function?
 > I have a Tiff image file, on it there's an almost round spot, e.g. 
laser profile.
 > Is there a way in mathematica to 2D Gaussian fit the spot?
 >


Hello,

The best way to do this would depend on the kinds of images you have 
(i.e. how noisy they are, how many spots are there, etc.)

The functions here could be useful to you:

http://reference.wolfram.com/mathematica/guide/SegmentationAnalysis.html

For example ComponentMeasurements will help measure the spot and also 
identify its centre.  Then you could cut the spot from the image and 
convert it to a matrix so you can use fitting methods such as those 
implemented in NonlinearModelFit.

I recommend looking at this blog post as well:

http://blog.wolfram.com/2012/01/04/how-to-count-cells-annihilate-sailboats-and-warp-the-mona-lisa/

-- 
Szabolcs Horvát
Visit Mathematica.SE:  http://mathematica.stackexchange.com/



  • Prev by Date: Re: Distinquishing #'s in nested pure functions
  • Next by Date: Re: Distinquishing #'s in nested pure functions
  • Previous by thread: 2D Gaussian fit
  • Next by thread: Re: 2D Gaussian fit