Posted by
Niko Ehrenfeuchter on
Nov 05, 2014; 12:55pm
URL: http://imagej.273.s1.nabble.com/Weka-Segmentation-probability-maps-tp5010292p5010312.html
Hi Ignacio,
thanks a lot, this is exactly what I've been looking for!
Cheers
~Niko
On 04.11.2014 18:50, Ignacio Arganda-Carreras wrote:
> Hello Niko,
>
> How many classes do you have? In principle, you should assign to each pixel
> the class with higher probability. This is what happens when you click in
> the GUI on "Create result".
>
> I just made a short Beanshell script that does exactly that:
>
>
https://gist.github.com/iarganda/c7fc0a88b8d2737c9d3d>
> Let me know if you need help with it.
>
> ignacio
>
> On Tue, Nov 4, 2014 at 4:26 PM, Niko Ehrenfeuchter <
>
[hidden email]> wrote:
>
>> Dear all,
>>
>> is there a quick way (or code snippet) to transform the probability maps
>> resulting from a Weka run into the other result format (segmentation map)?
>>
>> Thanks,
>> ~Niko
>> --
>> Niko Ehrenfeuchter | Image Analysis Specialist | Biozentrum, University of
>> Basel | Klingelbergstr. 50/70 | CH-4056 Basel
>> Phone: +41 (61) 26 72673 |
[hidden email] |
>> www.biozentrum.unibas.ch | www.microscopynetwork.unibas.ch
>>
>> --
>> ImageJ mailing list:
http://imagej.nih.gov/ij/list.html>>
>
>
>
--
Niko Ehrenfeuchter | Image Analysis Specialist | Biozentrum, University
of Basel | Klingelbergstr. 50/70 | CH-4056 Basel
Phone: +41 (61) 26 72673 |
[hidden email] |
www.biozentrum.unibas.ch | www.microscopynetwork.unibas.ch
--
ImageJ mailing list:
http://imagej.nih.gov/ij/list.html