Weka surely works, but can it be applied to 3D images using 3D features? If yes, that would be great for other purposes, too.
I often separate weft yarns from warp yarns by calculating local orientation using, e.g., the structure tensor method. Thresholding based on orientation separates the yarns very effectively.
>-----Original Message-----
>From: ImageJ Interest Group [mailto:
[hidden email]] On Behalf Of
>Ignacio Arganda-Carreras
>Sent: 7. lokakuuta 2015 18:24
>To:
[hidden email]
>Subject: Re: Yarns segmentation
>
>Hello Zag,
>
>You can give a try to the Trainable Weka Segmentation
><
http://fiji.sc/Trainable_Weka_Segmentation>.
>
>I converted your images to 8-bit and this is what I got using that plugin:
>
>[image: Inline image 1]
>
>These are my settings:
>
>[image: Inline image 2]
>
>I can send you the classifier I got if you want.
>
>Cheers!
>
>ignacio
>
>
>On Wed, Oct 7, 2015 at 2:06 PM, gvozdin <
[hidden email]> wrote:
>
>> Hi all!
>>
>> I have a stack of images of textile composite from X-Ray mCT (about
>> 1500 images, TIFF, 16bit). In this stack there are warp and weft yarns
>> (you can see an exapmple in images below). So i need to separate warp
>> yarns to one stack and weft yarns to the other for the further processing.
>> Have anyone an idea how to do that?
>> <
http://imagej.1557.x6.nabble.com/file/n5014571/Subvolume0490.png>
>> <
http://imagej.1557.x6.nabble.com/file/n5014571/Subvolume0509.png>
>>
>>
>>
>> --
>> View this message in context:
>>
http://imagej.1557.x6.nabble.com/Yarns-segmentation-tp5014571.html>> Sent from the ImageJ mailing list archive at Nabble.com.
>>
>> --
>> ImageJ mailing list:
http://imagej.nih.gov/ij/list.html>>
>
>
>
>--
>Ignacio Arganda-Carreras, Ph.D.
>Ikerbasque Research Fellow
>Departamento de Ciencias de la Computacion e Inteligencia Artificial Facultad
>de Informatica, Universidad del Pais Vasco Paseo de Manuel Lardizabal, 1
>20018 Donostia-San Sebastian
>Guipuzcoa, Spain
>
>Phone : +34 943 01 73 25
>Website:
http://sites.google.com/site/iargandacarreras/><
http://biocomp.cnb.csic.es/~iarganda/index_EN.html>
>
>--
>ImageJ mailing list:
http://imagej.nih.gov/ij/list.html