[ITK-users] Classification from a training text file

[Matt McCormick]

Hi Francisco,

It could be possible to import the data with CVSFileReader and then
convert the Array2D to an Image ImportImageFilter [2]. Note that
Array2D inherits from vnl_matrix [1], which has methods to access the
data. Let us know about your experiences.

Thanks,
Matt

[1] http://www.itk.org/Doxygen/html/classitk_1_1CSVArray2DFileReader.html

[2] http://www.itk.org/Doxygen/html/classitk_1_1ImportImageFilter.html

[3]

On Fri, Apr 17, 2015 at 9:02 AM, Francisco Lopez de la Franca
<franciscolopezdelafranca at gmail.com> wrote:
> Hi.
> I have a text file made up of N rows and M columns. Each row represents a
> measurement of M features, that is, Weka-styled.
> I could add a last column with the class of every measurement but it is
> optional.
>
> I've been havinig a look at the ITK classification classes (Bayesian,
> k-means, etc.), but they receive an image as input (e.g. a vector image).
>
> I'd like to know what is the best way, in my case, to perform the
> classification of the measurements stored in my training text file.
>
> Thank you very much in advance.
> My best regards.
>
> _____________________________________
> 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://public.kitware.com/mailman/listinfo/insight-users
>