multi phase segmentation marker-controlled watershed

classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|

multi phase segmentation marker-controlled watershed

PatrIM
Hi
I am working with a 3D image of a soil which contains 4 different materials.
I would like to segment it in 4 phases. I read that watershed works well so
I am trying to use  marker-controlled watershed, the one according with its
description requires

-The Input image: a 2D or 3D grayscale image to flood, usually the gradient
of an image.
-The Marker image: an image of the same dimensions as the input
containing the seed points or markers as connected regions of voxels, each
of them with a different label. They correspond usually to the local minima
of the input image, but they can be set arbitrarily.

For the input I generated a gradient using morpholobj/morphological filters
(3D)

But for the Marker I am having problems. I don’t know how to generate an
appropriate 3D image. Making use of global segmentation I generated an image
of 4 phases, expecting it could work as my marker. However giving this image
and my gradient to marker-controlled watershed it gives me back as a result
the marker 3D image.

Do you how can I generate and appropriate marker? Or how can I obtain my
segmentation in 4 phases?

Thanks in advance




--
Sent from: http://imagej.1557.x6.nabble.com/

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html
Reply | Threaded
Open this post in threaded view
|

Re: multi phase segmentation marker-controlled watershed

Frank Shaffer
Trainable Segmentation

On Mon, Mar 30, 2020, 5:19 AM PatrIM <[hidden email]> wrote:

> Hi
> I am working with a 3D image of a soil which contains 4 different
> materials.
> I would like to segment it in 4 phases. I read that watershed works well so
> I am trying to use  marker-controlled watershed, the one according with its
> description requires
>
> -The Input image: a 2D or 3D grayscale image to flood, usually the gradient
> of an image.
> -The Marker image: an image of the same dimensions as the input
> containing the seed points or markers as connected regions of voxels, each
> of them with a different label. They correspond usually to the local minima
> of the input image, but they can be set arbitrarily.
>
> For the input I generated a gradient using morpholobj/morphological filters
> (3D)
>
> But for the Marker I am having problems. I don’t know how to generate an
> appropriate 3D image. Making use of global segmentation I generated an
> image
> of 4 phases, expecting it could work as my marker. However giving this
> image
> and my gradient to marker-controlled watershed it gives me back as a result
> the marker 3D image.
>
> Do you how can I generate and appropriate marker? Or how can I obtain my
> segmentation in 4 phases?
>
> Thanks in advance
>
>
>
>
> --
> Sent from: http://imagej.1557.x6.nabble.com/
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
>

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html
Reply | Threaded
Open this post in threaded view
|

Re: multi phase segmentation marker-controlled watershed

Jeremy Adler
In reply to this post by PatrIM
You want to identify 4 different materials -
how do they differ, size/volume, shape, texture, fluorescence, elemental composition?
Their differences are the basis for separating them.

I would also suggest considering Multi Otsu thresholding, unlike many segmentation methods which divides the image into two areas based on the histogram of the image, Multi Otsu allows for up to 5 divisions.

Jeremy Adler
BioVis
Uppsala U



-----Original Message-----
From: ImageJ Interest Group <[hidden email]> On Behalf Of PatrIM
Sent: Monday, March 30, 2020 11:00 AM
To: [hidden email]
Subject: multi phase segmentation marker-controlled watershed

Hi
I am working with a 3D image of a soil which contains 4 different materials.
I would like to segment it in 4 phases. I read that watershed works well so I am trying to use  marker-controlled watershed, the one according with its description requires

-The Input image: a 2D or 3D grayscale image to flood, usually the gradient of an image.
-The Marker image: an image of the same dimensions as the input containing the seed points or markers as connected regions of voxels, each of them with a different label. They correspond usually to the local minima of the input image, but they can be set arbitrarily.

For the input I generated a gradient using morpholobj/morphological filters
(3D)

But for the Marker I am having problems. I don’t know how to generate an appropriate 3D image. Making use of global segmentation I generated an image of 4 phases, expecting it could work as my marker. However giving this image and my gradient to marker-controlled watershed it gives me back as a result the marker 3D image.

Do you how can I generate and appropriate marker? Or how can I obtain my segmentation in 4 phases?

Thanks in advance




--
Sent from: http://imagej.1557.x6.nabble.com/

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








När du har kontakt med oss på Uppsala universitet med e-post så innebär det att vi behandlar dina personuppgifter. För att läsa mer om hur vi gör det kan du läsa här: http://www.uu.se/om-uu/dataskydd-personuppgifter/

E-mailing Uppsala University means that we will process your personal data. For more information on how this is performed, please read here: http://www.uu.se/en/about-uu/data-protection-policy

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html
Reply | Threaded
Open this post in threaded view
|

Re: multi phase segmentation marker-controlled watershed

PatrIM
Hi
Thanks for your ideas, my 3D image comes from a micro CT, so the difference
on the materials is given by its density.
I used Otsu method as my global segmentation, but I want a local
segmentation.
My problem was using the plugin marker-controlled watershed which was (at
least for me) not clear how to create the marker but finally I succeed.
what I did was:
The marker is an image the global segmented image but with the boundary
borders voxels=0, in order to have a value 0 in the borders I binarized the
gradient and subtract it to the global segmented image.
With this marker and the gradient of my image the plugin works well.



--
Sent from: http://imagej.1557.x6.nabble.com/

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