[Insight-users] Registration method

[Pierre JUILLARD]

Hi Nour and Luis,


Thank you for your answer Luis It is also a subject of interest for me.

I have been studying publications describing different ICP algorithms (one
is mainly interesting:
http://www.cs.princeton.edu/~smr/papers/fasticp/fasticp_paper.pdf), as well
as others describing methods for the the global registration step.

As noticed, ICP methods are interesting only when the two data sets are
already (even if roughly) on top of each other. These methods can be
implemented with ITK. However, what about the global registration step?

Most particulary, I have read about a method described in this paper:
http://graphics.stanford.edu/~ngelfand/papers/global/gelfand-robust-global-05.pdf
and more particularly in this thesis:
http://graphics.stanford.edu/~ngelfand/papers/thesis/thesis.pdf

It explains how to setup what seems a quite efficient method (computation
time as well as accuracy) to fufill the first step of registration (even for
datasets having just small overlapping areas): the global registration
method makes use of different concepts:

- it is a method using *shape descriptors*, based on *performing integral
operations on the underlying shape*, for identifying features in the data
and selecting potential correspondence points in the model.

- among the datasets, a scale-space representation of the volume descriptor
together with a persistence algorithm allows robustly selecting feature
points at multiple scales

- the quality of the correspondence based on the coordinates of the feature
points (selected using the integral volume descriptors) between the target
and the source datasets is evaluated with the *distance root mean squared
error*, or *dRMS*.

- if validated, a Correspondence Search is carried out.


As this method seems quite efficient, do you know if it is possible to
implement it with ITK? Most notably, are the basic algortihms available (I
am thinking to classes that would compute over a dataset the integral volume
descriptor, the distance root mean square, branch-and-bound algorithm,
etc...)?

I thank you in avance for your help.


Regards,


Pierre




2008/12/7 Luis Ibanez <luis.ibanez at kitware.com>

>
> Hi Nour,
>
>
>             Welcome to ITK !
>
>
> Yes,
> you can do PointSet registration with ITK.
>
>
> Please do the following:
>
>
> 1) Build ITK by turning ON the ITK_USE_REVIEW (advanced) flag in CMake.
>
>
> 2) Use the itkVTKPolyDataReader.h class that you can find in
>   Insight/Code/Review, in order to load the two polydata files
>   into ITK. This will read legacy files in .vtk format.
>
>   If you have VRML file, then convert them first to .vtk files.
>   You can do this by using VTK readers and writers.
>
>
> 3) Use the ICP method, as described in the examples:
>
>      Insight/Examples/Patented
>         IterativeClosestPoint1.cxx
>         IterativeClosestPoint2.cxx
>         IterativeClosestPoint3.cxx
>
>
>    Please note that the patent on the ICP method has expired,
>    so you don't have to worry about it at this point.
>
>
>
>   Regards,
>
>
>      Luis
>
>
> --------------------
> Nour Mestiri wrote:
>
>> Hi all ITK users,
>> I'm new with you so please don't blame me if my questions are evident and
>> try to help me if possible.
>> I wanna do the registration of 2 objects (polydatas generated from vrml
>> files).
>> Is it possible? Is there a code example which allows to make that?
>> Please i need help.
>> Thank you so much
>>
>>
>>
>> ------------------------------------------------------------------------
>>
>> _______________________________________________
>> Insight-users mailing list
>> Insight-users at itk.org
>> http://www.itk.org/mailman/listinfo/insight-users
>>
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20081207/e516b113/attachment.htm>