[Insight-users] Is there an image filter that can compute an mean image (mean pixel values) of several images with different sizes?

Dawood Masslawi masslawi at gmail.com
Mon Dec 20 20:05:39 EST 2010


Since you want to average over multiple objects it's best to assign a different iterator for
each object. After that you can define the overlapping region and use a "for" or "while" loop
for all iterators simultaneously, this way you can get the intensity values at the desired
indices and compute the mean values. Also, chapter 11 of the ITK software guide has
considerable amount of useful information regarding the ITK iterators.
Best regards,
Dawood.
--- On Mon, 12/20/10, Haiyong Xu <haiyeong at gmail.com> wrote:

From: Haiyong Xu <haiyeong at gmail.com>
Subject: Re: Is there an image filter that can compute an mean image (mean pixel values) of several images with different sizes?
To: "Dawood Masslawi" <masslawi at gmail.com>
Cc: insight-users at itk.org
Date: Monday, December 20, 2010, 2:33 PM

Thanks for the answer, Dawood. Would you like to provide more information about how to define a neighborhood iterators that can span several itk::Image<> objects? 

Regrads,
Haiyong




On Mon, Dec 20, 2010 at 10:51 AM, Dawood Masslawi <masslawi at gmail.com> wrote:

Dear Haiyong,You can use the neighborhood iterators to define a window and

calculate the mean intensity value in that window by averaging
over the defined neighborhood.
Best regards,
Dawood Masslawi


>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<

>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<

Hi insight-users,

I have several subvolume images that were manually cropped from CT
abdominal studies. These images have different sizes. I need calculate
a mean image with the pixel value equals to the mean value of pixels
in the subvolume images. Since the subvolume images have different
sizes, the mean image's size will be set to the overlapped region of
all subvolume images. I wander if there any ITK filter can do the job.
Otherwise, I may implement one by myself. Thanks.

Regards,
Haiyong Xu








      




      
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20101220/f709a8cd/attachment.htm>


More information about the Insight-users mailing list