Login  Register

Re: finding objects of the same colour

Posted by ludwiczakagnieszka on Oct 04, 2014; 2:03pm
URL: http://imagej.273.s1.nabble.com/finding-objects-of-the-same-colour-tp5009883p5009902.html

W dniu 2014-10-04 01:39, Stoyan Pavlov [via ImageJ] pisze:
Hi Ludwickzaka,
Seems like you need to combine several different approaches - color based,
shape and texture...  You may try the Weka segmentation (build into Fiji),
or Cell profiler (separate software based on ImageJ).

Best wishes
Stoyan
 На 03.10.2014 20:08 "ludwiczakagnieszka" <[hidden email]>
написа:

> W dniu 2014-10-03 11:38, Michael Schmid-3 [via ImageJ] pisze:
> > Hi Ludwiczaka,
> >
> > a few ideas:
> >
> > - Try edge sharpening, e.g. use the 'Thresholded Blur' plugin, it can
> > be also used to sharpen edges
> >
> http://imagejdocu.tudor.lu/doku.php?id=plugin:filter:thresholded_blur:start
> >
> > - If you have an RGB image with different colors, try Gabriel
> > Landini's color deconvolution plugin (built-in in Fiji)
> > http://www.mecourse.com/landinig/software/software.html
> > or the Versatile wand (in contrast to the Wand of ImageJ, it's color
> > sensitive)
> >
> http://imagejdocu.tudor.lu/doku.php?id=plugin:segmentation:versatile_wand:start
> >
> > Michael
> > ________________________________________________________________
> >
> > On Oct 3, 2014, at 09:13, ludwiczakagnieszka wrote:
> >
> > > Hi everyone.
> > >
> > > I'm working on images of muscles anatomical and ultrasonic images.
> > My aim is
> > > to detect marbling - its the fat inside the muscle, visible on the
> > muscle
> > > cross section in form of a net of white particles. I've already tried
> > > tresholding and different edge detectors. Tresholding seems do be
> > the best
> > > so far, but the edge detectors work unproperly on the type of images
> > I'm
> > > working with. I want to find some additional tool except for the
> > > tresholding.  Maybe it should find objects with thi same colour??
> > Maybe you
> > > can give me some guidelines what may be the best for this purpose?
> > >
> > > Thank you in advance.
> > >
> > >
> > >
> > > --
> > > View this message in context:
> >
> http://imagej.1557.x6.nabble.com/finding-objects-of-the-same-colour-tp5009883.html
> > > Sent from the ImageJ mailing list archive at Nabble.com.
> > >
> > > --
> > > ImageJ mailing list: http://imagej.nih.gov/ij/list.html
> >
> > --
> > ImageJ mailing list: http://imagej.nih.gov/ij/list.html
> >
> >
> > ------------------------------------------------------------------------
> > If you reply to this email, your message will be added to the
> > discussion below:
> >
> http://imagej.1557.x6.nabble.com/finding-objects-of-the-same-colour-tp5009883p5009886.html
> >
> > To unsubscribe from finding objects of the same colour, click here
> > <
> >.
> > NAML
> > <
>
http://imagej.1557.x6.nabble.com/template/NamlServlet.jtp?macro=macro_viewer&id=instant_html%21nabble%3Aemail.naml&base=nabble.naml.namespaces.BasicNamespace-nabble.view.web.template.NabbleNamespace-nabble.view.web.template.NodeNamespace&breadcrumbs=notify_subscribers%21nabble%3Aemail.naml-instant_emails%21nabble%3Aemail.naml-send_instant_email%21nabble%3Aemail.naml
> >
> >
> Thank you very much. I'll try all the options right away and let know
> about the effects.
>
> Kind regards,
> Agnieszka.
>
>
>
>
> --
> View this message in context:
> http://imagej.1557.x6.nabble.com/finding-objects-of-the-same-colour-tp5009883p5009896.html
> Sent from the ImageJ mailing list archive at Nabble.com.
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
>

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



If you reply to this email, your message will be added to the discussion below:
http://imagej.1557.x6.nabble.com/finding-objects-of-the-same-colour-tp5009883p5009899.html
To unsubscribe from finding objects of the same colour, click here.
NAML
Thank you very much.

Regards,
Agnieszka.