[Insight-users] Weird result from Point Set Registration

[Luis Ibanez]

Hi Junyi,


You *must* initialize the transform to a value closer
to the real misalignment between the two point sets.

The geometrical arrangement of points that you have
is particularly prone to mis-correspondance between
the points.


As you probably know, pointset-to-pointset registration
is actually trying two solve to separate but related
problems:

           1) Point correspondance
           2) Registration


If you don't initialize the Transform to a value closer
to the real mis-alignment, then the point will probably
find wrong correspondances that satisfy a local minimum
in the sum of squared distances.



    Regards,


       Luis



------------------
Junyi Xia wrote:
> Hi there,
>     After replacing the example points used in the IterativeClosetPoint2 
> with my test points, I found the output of the IterativeClosetPoint2 
> seems weird. Each of the fixed and the moving points  contain 6 points 
> as shown in the following:
> Fixed points:
> 
> 0 5 0
> 0 -5 0
> -5 0 0
> 0 0 5
> 0 0 -5
> 5 0 0
> Moving points:
> 
> 5 5 0
> 5 -5 0
> 0 0 0
> 5 0 5
> 5 0 -5
> 10 0 0
> The true displace should be -5 on the x direction, however the program 
> returns:
> Number of fixed Points = 6
> Number of moving Points = 6
> Solution = [-574253, -6.61669, -5.83746, -3.57322, -0.930079, 0.147961]
> 
> Is there any parameters I need to tune? Thanks
> 
> - Junyi
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
> 
>