[Insight-users] Hints to create a known deformation image - Deformable Image registration?

[motes motes]

Thanks both of you. But should the optimizer not have something to
move in to find the peak of the cost function? I have previously used
a white image with a single black box and the result was very poor
when using eg. gradient based optimizer.

I was thinking that the same problem would occur if I made a white
image with a black grid.




On Mon, Nov 2, 2009 at 12:17 AM, Nicholas Tustison <ntustison at gmail.com> wrote:
> Hi Luis, Motes,
>
> Another possibility you might want to consider
>
> http://public.kitware.com/Insight/Doxygen/html/classitk_1_1GridImageSource.html
>
> Nick
>
>
> On Nov 1, 2009, at 6:06 PM, Luis Ibanez wrote:
>
>> Hi Motes,
>>
>> 1) Lena is certainly not the best motif for evaluating a deformable
>>    registration process. You may want to use a grid image with
>>    about four time the density of lines of the BSpline grid, and
>>    lines that are more than 2 pixels apart.
>>
>>    The reason why you want lines to be more than 2 pixels apart
>>    is to avoid aliasing when you resample the image using the
>>    deformation field.
>>
>> 2) You could create such image by using GIMP
>>
>>      a) Open Gimp
>>      b) create a new image,
>>      c) Select Filters --> Render--> Pattern --> Grid
>>      d) save the image
>>
>>
>> 3)  Yes, you can make more detailed initial deformation...
>>      but you have to initialize all the coefficients.
>>
>>      It may be desirable to generate those initial numbers
>>       from a program...
>>
>>
>>   Regards,
>>
>>
>>         Luis
>>
>>
>> --------------------------------------------------------------------
>>
>> On Fri, Oct 30, 2009 at 2:25 PM, motes motes <mort.motes at gmail.com> wrote:
>>>
>>> I would like to test my BSplineDeformable registration method with a
>>> known deformation field. Currently I apply the BSplineWarping1.cxx
>>> example to the fixed image and use the output as the moving image. As
>>> input image I use lena:
>>>
>>> http://stochastix.files.wordpress.com/2008/07/lena-sjooblom.jpg
>>>
>>> But are there better motives that illustrate the deformation better
>>> (like a chess board, salt/pebber image etc)?
>>>
>>> And is it possible to create a more detailed know deformation instead
>>> of only changing the 8*8 deformation vectors in the text input file to
>>> the warper?
>>> _____________________________________
>>> 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.html
>>>
>>> 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://www.itk.org/mailman/listinfo/insight-users
>>>
>> _____________________________________
>> 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.html
>>
>> 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://www.itk.org/mailman/listinfo/insight-users
>
>