hey juan, i am using threshold_otsu for thresholding but i am not getting appropriate result. And how to use threshold_adapt? i want to convert gray image to binary image. how can i do? anybody help in this problem. thanks On Thursday, October 3, 2013 7:28:44 AM UTC+5:30, Juan Nunez-Iglesias wrote:
Hi Stefan,
I hope this isn't too late. I recently had to segment out the chromosomes in this picture:
[image: Inline image 1]
You can see the illumination is really uneven, so `threshold_otsu` does really poorly. `threshold_adapt` works as advertised but you get some artifacts:
[image: Inline image 2]
The key to getting around this was seeing the "grain" in the outside regions compared to the chromosomes themselves. So after a `binary_opening` with the right parameters (don't have them off the top of my head), followed by a `remove_small_objects`:
[image: Inline image 3]
Hope that helps!
Juan.
PS: I also made this notebook<http://nbviewer.ipython.org/urls/github.com/jni/notebooks/raw/master/potholes.ipynb>to help Mehmet Kunt, a civil engineering professor Emmanuelle and I met at EuroSciPy, measure potholes in images.
On Thu, Oct 3, 2013 at 2:21 AM, Stéfan van der Walt <ste...@sun.ac.za<javascript:>
wrote:
Hi folks,
I'm giving a talk on skimage at PyCon ZA tomorrow. I still have room for a few screenshots or for one demo. If anyone has a particularly nice example, please send it my way.
Thanks! Stéfan
-- You received this message because you are subscribed to the Google Groups "scikit-image" group. To unsubscribe from this group and stop receiving emails from it, send an email to scikit-image...@googlegroups.com <javascript:>. For more options, visit https://groups.google.com/groups/opt_out.
participants (1)
-
Payal Gupta