border artefacts with skimage.exposure.equalize_adapthist
Josh Warner
silvertrumpet999 at gmail.com
Sat Jan 24 18:41:25 EST 2015
Just to confirm what Steven said, building from current master and applying
your command to your `nuclei.jpg` image I obtain the attached image without
artifacts.
0.11 should be released fairly soon, but if you need this sooner you can
build from source. We'd be happy to help if you run into problems.
Josh
On Saturday, January 24, 2015 at 4:46:23 AM UTC-7, Kai Wiechen wrote:
>
>
> <https://lh3.googleusercontent.com/-JDkNXe7k44s/VMOE-xwgPXI/AAAAAAAABLA/STWxQlQkU9Q/s1600/nuclei.jpg>
> <https://lh3.googleusercontent.com/-sgqpXIXHhF0/VMOFDbcK8sI/AAAAAAAABLI/iHcFERpbFfc/s1600/nuclei_clahe.jpg>
> Hello,
>
> I am new to scikit-image (and python too), but found the combination of
> scikit-image implementation of algorithms together with ndarrays extremely
> powerful.
>
> For now, I am trying to find nuclei in microscopic images (color
> deconvolution, find seeds with blob_log) This works fairly well but due to
> low contrast some nuclei are not detected.
>
> nuclei_clahe = equalize_adapthist(nuclei)
>
> gives much better local contrast but introduces linear artefacts at the
> test image borders. Is it possible to avoid/reduce this?
>
> Best regards,
>
>
> Kai
>
>
>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/scikit-image/attachments/20150124/168f9f26/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: nuclei_dev.png
Type: image/png
Size: 67053 bytes
Desc: not available
URL: <http://mail.python.org/pipermail/scikit-image/attachments/20150124/168f9f26/attachment.png>
More information about the scikit-image
mailing list