[Insight-users] skeleton extraction

Sergio Vera sergio.vera at alma3d.com
Fri Mar 1 10:41:18 EST 2013


Hi

I see. It seems that  itk::BinaryThinningImageFilter. does not have any
methoid for selecting the connectivity of the final skeleton.
You can try to change the fikter yourself and use 8 connectivity instead of
4 connectivity. But I dont know if this will be easy or not.

Alternatively, you can try a coupe of methods published in the insight
journal (search for skeleton or thinning) and see if they generate
8-connected skeletons

best regards


On Fri, Mar 1, 2013 at 7:09 AM, Vardhan, Vishnu
<vishnu.vardhan at philips.com>wrote:

>  Hi,****
>
>      I am working on 2D images. I need skeletons that are maximally thin.*
> ***
>
> ** **
>
> This is the kind of skeleton I want to obtain and also similar to the one
> obtained from MATLAB.****
>
> ****
>
> ** **
>
> However, when I implemented it using ITK, the result is similar to the
> following:****
>
> ****
>
> ** **
>
> I need a method to acquire a skeleton minimally connected( as in first
> figure), that is devoid of ‘L’ shapes(as present in second figure)****
>
> ** **
>
> *From:* Sergio Vera [mailto:sergio.vera at alma3d.com]
> *Sent:* 28 February 2013 13:31
> *To:* Vardhan, Vishnu
> *Cc:* insight-users at itk.org
> *Subject:* Re: [Insight-users] skeleton extraction****
>
> ** **
>
> What kind of images are trying to skeletonize? (3D-2D, what kind of
> skeletons do you need...)****
>
> ** **
>
> ITK does not have many methods for skeletonizartion. There are a bunch of
> methods in the insight journal but it pretty much depends on the object and
> what do you expect in return.****
>
> ** **
>
> Sergio****
>
> ** **
>
> On Wed, Feb 27, 2013 at 10:46 AM, Vardhan, Vishnu <
> vishnu.vardhan at philips.com> wrote:****
>
> Hi,****
>
>      I have extracted skeleton of an image using ITK using
> itk::BinaryThinningImageFilter. I have tried the same with MATLAB using
> the function *bwmorph(im,’skel’,Inf) *and I find the results different.
> Actually, I find the result from MATLAB better. Is there any other way to
> obtain skeleton of an image using ITK?****
>
> Thanks in advance.****
>
> ** **
>  ------------------------------
>
> The information contained in this message may be confidential and legally
> protected under applicable law. The message is intended solely for the
> addressee(s). If you are not the intended recipient, you are hereby
> notified that any use, forwarding, dissemination, or reproduction of this
> message is strictly prohibited and may be unlawful. If you are not the
> intended recipient, please contact the sender by return e-mail and destroy
> all copies of the original message.****
>
>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://www.itk.org/mailman/listinfo/insight-users****
>
>
>
> ****
>
> ** **
>
> --
> Sergio Vera
>
>  Alma IT Systems
>  C/ Vilana, 4B, 4º 1ª
>  08022 Barcelona
>  T. (+34) 932 380 592
>  www.alma3d.com ****
>



-- 
Sergio Vera

 Alma IT Systems
 C/ Vilana, 4B, 4º 1ª
 08022 Barcelona
 T. (+34) 932 380 592
 www.alma3d.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20130301/639af349/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/jpeg
Size: 6662 bytes
Desc: not available
URL: <http://www.itk.org/pipermail/insight-users/attachments/20130301/639af349/attachment-0002.jpeg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: image/jpeg
Size: 6093 bytes
Desc: not available
URL: <http://www.itk.org/pipermail/insight-users/attachments/20130301/639af349/attachment-0003.jpeg>


More information about the Insight-users mailing list