[ITK-users] Registration taking longer to start in 4.7.1?

[Matias Montroull]

oh lord, sorry to fill your inbox, I included my code again and
called: fixedNormalizer->Update();

That did the trick.

Sorry folks, I just ended up answering my own stupid question.

Regards,

Matias.

On Sat, Apr 25, 2015 at 10:44 AM, Matias Montroull <matimontg at gmail.com>
wrote:

> Disregard my message... For some reason, in this new version of ITK, if I
> use the *NormalizeImageFilter*, tehn the images end up not overlapping.
>
> Any clue what changed on that filter?
>
> This is the code I had to remove:
>
> typedef itk::NormalizeImageFilter<FixedImageType, InternalImageType>
> NormalizeFilterType;
> NormalizeFilterType::Pointer fixedNormalizer = NormalizeFilterType::New();
> NormalizeFilterType::Pointer movingNormalizer = NormalizeFilterType::New();
>
> fixedNormalizer->SetInput(fixedImageReader->GetOutput());
> movingNormalizer->SetInput(movingImageReader->GetOutput());
>
> typedef itk::DiscreteGaussianImageFilter<InternalImageType,
> InternalImageType> GaussianFilterType;
>
> GaussianFilterType::Pointer fixedSmoother = GaussianFilterType::New();
> GaussianFilterType::Pointer movingSmoother = GaussianFilterType::New();
>
> fixedSmoother->SetVariance(2.0);
> movingSmoother->SetVariance(2.0);
>
> fixedSmoother->SetInput(fixedNormalizer->GetOutput());
> movingSmoother->SetInput(movingNormalizer->GetOutput());
>
> registration->SetFixedImage(fixedSmoother->GetOutput());
> registration->SetMovingImage(movingSmoother->GetOutput());
>
> Thanks,
>
> Matias.
>
> On Sat, Apr 25, 2015 at 9:55 AM, Matias Montroull <matimontg at gmail.com>
> wrote:
>
>> Something I noticed is that version 4.7.1 may be more strict when it
>> comes to origin.. My 2 images have different origins and that may be the
>> reason.
>>
>> How can I set both images to have the same origin? is it safe or should I
>> modify the parameters to make them overlap?
>>
>> Thanks,
>>
>> Matias.
>>
>> On Sat, Apr 25, 2015 at 9:12 AM, Matias Montroull <matimontg at gmail.com>
>> wrote:
>>
>>> Hi,
>>>
>>> I downloaded and compiled version 4.7.1 of ITK and then recompiled a
>>> source code I had for *3D* MuttualInformation Registration
>>>
>>> I noticed it now takes longer for registration to start and for some
>>> reason I now get joint pdf sum med to zero (and I didn't change anything on
>>> my code).
>>>
>>> Is there a known issue with the time it takes for registration to start?
>>>
>>> Thank you,
>>>
>>> Matias.
>>>
>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20150425/957471b6/attachment.html>