[Insight-developers] Pattern Intensity Similarity Metric

[Luis Ibanez]

Hi John,

You are right, the current "PatternIntensityMetric"
doesn't follow the description of the original paper.

Lydia raised this same concern recently while she
was describing this metric for the Registration chapter
of the theory book.

It seems that the right thing to do is to rename the
current ITK class to something else in order to avoid
confusion.



In that way, if you want to implement the 'real'
PatternIntensityMetric the right name will be
available.

Feel free to go ahead and use the name for your metric,
but please hold on checking it in until we rename the
current ITK metric.


Regards,


    Luis



--------------------
John Hipwell wrote:
> 
> Can anyone tell me the origins of "PatternIntensityImageToImageMetric"?
> 
> We have said that we'd implement this metric, or at least one with the 
> same name as described in:
> 
> Weese, J. and Buzug, T. M. and Lorenz, C. and Fassnacht, C.,
> "An Approach to 2D/3D Registration of a Vertebra in 2D X-Ray
>  Fluoroscopies with 3D CT Images", Proc. CVRMed/MRCAS 1997, volume 1205, 
> 119-128.
> 
> The implementation in "PatternIntensityImageToImageMetric" doesn't seem 
> to correspond to the above reference so rather than modifying the former 
> I'm tempted to implement a new metric called 
> "WeesePatternIntensityImageToImageMetric".
> 
> John Hipwell
> 
> 
>  ----------------------------------------------------------------------
>  Imaging Sciences,
>  5th Floor Thomas Guy House,
>  Guy's Hospital,
>  King's College London,
>  London Bridge,                                Tel: +44 (0)20 7955 2380
>  London,                                       Fax: +44 (0)20 7955 4532
>  SE1 9RT.                                     http://www-ipg . umds . ac . uk
> 
> _______________________________________________
> Insight-developers mailing list
> Insight-developers at itk . org
> http://www . itk . org/mailman/listinfo/insight-developers
>