Re: Water-shedding non-circular objects (w/ Attachment)

Posted by gankaku on
URL: http://imagej.273.s1.nabble.com/Water-shedding-non-circular-objects-w-Attachment-tp5012071p5012074.html

Dear Clay,

as Niko mentioned the watershed Irregular Features might help. but its
purpose is to prevent overfragmentation as sometimes produced by the normal
watershed algorithm in ImageJ.
Nevertheless, it is based on the normal watershed. So if your connections
will not be split up correctly by the normal watershed you will also hit
the limit with the toolbox watershed.

There is another adjustable watershedding algorithm from Michael Schmid (if
I am not wrong) which is also worth a trial.

cheers,
Jan

2015-03-19 22:36 GMT+01:00 Clay Morton <
[hidden email]>:

>  Hey good people, I was wondering if anyone knew of a way to successfully
> separate touching particles that are not circular is shape. It seems that
> the water-shedding function only separates touching particles if they are
> circular, but has difficulty in correctly separating different shapes.
> Attached is an image that I have been working with. As you can see when a
> "crescent" shaped cell (sickle cell) is touching a circular cell (flat red
> blood cell), proper division does not occur. Also elliptical cells are
> sometimes cut in half (lower middle image).?Any ideas how I could correct
> this?
>
> Thanks
>
>
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html




--

CEO: Dr. rer. nat. Jan Brocher
phone:  +49 (0)6234 917 03 39
mobile: +49 (0)176 705 746 81
e-mail: [hidden email]
info: [hidden email]
inquiries: [hidden email]
web: www.biovoxxel.de

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