Isolating an object in image

[Sophie Lorent]

Hi,

I am trying to isolate unicellular algae from an image. I have tried to use filters, thresholds, math, gamma …

But the sometimes the inside of my cells are as nearly the same light  colour as the background. When this happens on the border of the cell, this part will be cut off the cell without being able to save it by “filling the holes” like I do it when these light parts occur in the middle on the cell. (See attachment figure 1 and 2)

Is there something that can make can make kind on join two edges? (See figures 1 and 2). Or if someone has a good idea on how I could solve this problem.

Cheers,

Sophie

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

[ctrueden]

Hi Sophie,

> I am trying to isolate unicellular algae from an image. I have tried
> to use filters, thresholds, math, gamma ...

Did you try the Trainable Weka Segmentation plugin?
http://fiji.sc/Trainable_Weka_Segmentation

It is bundled with the Fiji distribution of ImageJ: http://fiji.sc/

Regards,
Curtis

P.S. The ImageJ mailing list strips attachments so yours did not come
through.

P.P.S. See also: http://fiji.sc/Segmentation


On Mon, Mar 3, 2014 at 8:10 AM, Sophie Lorent <[hidden email]>wrote:

> Hi,
>
> I am trying to isolate unicellular algae from an image. I have tried to
> use filters, thresholds, math, gamma ...
>
> But the sometimes the inside of my cells are as nearly the same light
>  colour as the background. When this happens on the border of the cell,
> this part will be cut off the cell without being able to save it by
> "filling the holes" like I do it when these light parts occur in the middle
> on the cell. (See attachment figure 1 and 2)
>
> Is there something that can make can make kind on join two edges? (See
> figures 1 and 2). Or if someone has a good idea on how I could solve this
> problem.
>
> Cheers,
>
> Sophie
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
>

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