[Insight-users] itkScalarChanAndVeseSparseLevelSetImageFilter - RMS Change

[Kishore Mosaliganti]

Hi Eleni,

The RMS change values are now computed after reinitialization to signed
distance functions. So, it will now show up as small values. Remember to
download the latest CVS version.

Kishore

On Mon, Sep 7, 2009 at 8:06 PM, Sgouritsa, Eleni <esgourit at central.uh.edu>wrote:

>  Hello Kishore,
> I am sorry for the multiple e-mails. Please let me know about any progress
> in the issue with the high RMS change values. Do you also face the same
> problem?
>
> Best regards,
> Eleni
>
>
> -----Original Message-----
> From: Sgouritsa, Eleni
> Sent: Tue 8/25/2009 12:40 PM
> To: Kishore Mosaliganti; insight-users at itk.org
> Subject: RE: [Insight-users] itkScalarChanAndVeseSparseLevelSetImageFilter
> - RMS Change
>
> Hello Kishore,
> do you have any updates?
>
> Best wishes,
> Eleni
>
>
> -----Original Message-----
> From: Sgouritsa, Eleni
> Sent: Tue 8/18/2009 9:59 AM
> To: Kishore Mosaliganti; insight-users at itk.org
> Subject: RE: [Insight-users] itkScalarChanAndVeseSparseLevelSetImageFilter
> - RMS Change
>
> Hello Kishore,
>
> thank you for your answer. Let me clarify myself: I am currently just
> working on the sparse case. My problem is that I get very high values of RMS
> Change between
> the iterations of the level set. As you said, RMS values are used for
> indicating the convergence of the evolution. I would expect them to be
> around lets say 0.1 near convergence but I get all the time very high
> changes during the evolution, RMS change values like 263450, meaning huge
> numbers.
> Do you know why is this happening?
> Thank you very much.
>
> Regards,
> Eleni
>
>
> -----Original Message-----
> From: Kishore Mosaliganti [mailto:kishoreraom at gmail.com<kishoreraom at gmail.com>
> ]
> Sent: Tue 8/18/2009 9:07 AM
> To: Sgouritsa, Eleni ; insight-users at itk.org
> Subject: Re: [Insight-users] itkScalarChanAndVeseSparseLevelSetImageFilter
> - RMS Change
>
> Hi Eleni,
>
> I am back at work :).
>
> Ok, we made several corrections to the code in the past two months and you
> can download the latest CVS version. Many thanks for your feedback on using
> the code. It helped us identify bugs and clean up the code further.
>
> Your question was regarding the RMS Error values computed by the Dense and
> Sparse filters on the same image producing different values.
>
> The dense filter works on the levelset function defined on the whole image
> domain. As a result, the RMS values are computed on changes in the function
> everywhere.
>
> The sparse filter works only locally to the 0 level-set (hence the name
> sparse). The RMS values look at a small band of pixels. Therefore, the
> values in this case are at a different range.
>
> Irrespective, the RMS values are used for indicating the convergence of the
> evolution. Is there any reason why you want them to be at the same range ?
>
> Best,
> Kishore
>
> On Mon, Aug 17, 2009 at 6:37 PM, Sgouritsa, Eleni
> <esgourit at central.uh.edu>wrote:
>
> >  Hello,
> > I hope everything went well concerning the embassy.
> > Do you have any updates for the high RMS values? Was this problem fixed?
> >
> > Regards,
> > Eleni
> >
> >
> >
> > -----Original Message-----
> > From: alex gouaillard [mailto:alexandre_gouaillard at hms.harvard.edu<alexandre_gouaillard at hms.harvard.edu>
> <alexandre_gouaillard at hms.harvard.edu>
> > ]
> > Sent: Thu 7/2/2009 2:32 PM
> > To: Sgouritsa, Eleni
> > Cc: insight-users at itk.org
> > Subject: Re: [Insight-users]
> itkScalarChanAndVeseSparseLevelSetImageFilter
> > - RMS Change
> >
> > hi eleni,
> >
> > Kishore has been release by the US embassy in India (without any
> > ransom shall I had) and should be back in town july 9th.
> >
> > We will adress this issue right after that and keep you informed.
> >
> > thanks again for your feedback.
> >
> > alex.
> >
> >
> > On Jul 2, 2009, at 12:53 PM, Sgouritsa, Eleni wrote:
> >
> > > Hello,
> > > I still have a problem with very high values of RMS Change between
> > > the iterations of the level set. Any help or direction on how to
> > > solve this would be appreciated a lot.
> > > Thank you very much.
> > >
> > > Best regards,
> > > Eleni
> > >
> > > <ATT00001.txt>
> >
> >
> >
> > _____________________________________
> > Powered by www.kitware.com
> >
> > Visit other Kitware open-source projects at
> > http://www.kitware.com/opensource/opensource.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
> >
> >
>
>
>
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20090908/32271414/attachment.htm>