[ITK-users] SimpleITK for Java Image Fusion and Co-registration?

[Dženan Zukić]

Hi Ivan,

the optimizers in ITK minimize the metric, and since mutual information
needs to be "bigger" it is prefixed by a minus so that optimizers try to
increase its absolute value.

Regards,
Dženan

On Wed, Oct 5, 2016 at 8:34 AM, ivan <ivan.granata.na at gmail.com> wrote:

> with my example where i use
>
>
>   R.setMetricAsMattesMutualInformation(numberOfBins);
>
>   double LearningRate = 8.0;
>   double minStep = 0.001;
>   long numberOfIterations = 100;
>   double relaxationFactor = 0.5;
>   double gradientMagnitudeTolerance = 1e-006;
>
>   R.setOptimizerAsRegularStepGradientDescent
>
>
>
>  i receive a txt file and this video output
>
>   0 =   -0,15630 : [0,746321, -7,955376]
>   1 =   -0,17854 : [1,437118, -15,910358]
>   2 =   -0,19452 : [1,031387, -23,317717]
>   3 =   -0,20341 : [3,410042, -21,038059]
>   4 =   -0,19856 : [1,526970, -21,439759]
>   5 =   -0,20108 : [0,143113, -22,783732]
>   6 =   -0,20340 : [1,089391, -22,619125]
>   7 =   -0,20366 : [1,647981, -21,912288]
>   8 =   -0,20073 : [1,184824, -22,085392]
>   9 =   -0,20140 : [0,993548, -22,508374]
>  10 =   -0,20281 : [1,192105, -22,356475]
>  11 =   -0,20253 : [1,117475, -22,167086]
>  12 =   -0,20169 : [1,075827, -22,241268]
>  13 =   -0,20225 : [1,126952, -22,206076]
>  14 =   -0,20222 : [1,122912, -22,147089]
>  15 =   -0,20209 : [1,108291, -22,166964]
>  16 =   -0,20222 : [1,118988, -22,159212]
>  17 =   -0,20224 : [1,125776, -22,145295]
>  18 =   -0,20224 : [1,118157, -22,146866]
>  19 =   -0,20226 : [1,119790, -22,149387]
> -------
> itk::simple::Transform
>  TranslationTransform (0000000019CD54D0)
>    RTTI typeinfo:   class itk::TranslationTransform<double,3>
>    Reference Count: 3
>    Modified Time: 2659
>    Debug: Off
>    Object Name:
>    Observers:
>      none
>    Offset: [1.11979, -22.1494, 4.96231]
>
> Optimizer stop condition: RegularStepGradientDescentOptimizerv4: Gradient
> magnitude tolerance met after 20 iterations. Gradient magnitude (9.89e-007)
> is less than gradient magnitude tolerance (1e-006).
>  Iteration: 21
>  Metric value: -0,202264
>
>
>
>
> --
> View this message in context: http://itk-users.7.n7.nabble.
> com/ITK-users-SimpleITK-for-Java-Image-Fusion-and-Co-
> registration-tp37600p37640.html
> Sent from the ITK - Users mailing list archive at Nabble.com.
> _____________________________________
> 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
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20161006/90a5ed5c/attachment.html>