GSoC Blog updated

[Chintak Sheth]

Hi Jerome

Could you send me a couple of image samples ? I'd love to see if we can do
better than GIMP. :D

However, the two posts are essentially for Texture Synthesis in the sense
that it will be able to beautifully reconstruct the damaged portion if it
already exists in the image. Ive also implemented Fast Marching Method
algorithm which is essentially a Structural inpainting algorithm. PR #663
(in case you want to check it out)

Chintak
On Sep 5, 2013 5:19 PM, "Jerome Kieffer" <google at terre-adelie.org> wrote:

> On Thu, 5 Sep 2013 15:37:17 +0530
> Chintak Sheth <chintaksheth at gmail.com> wrote:
>
> > Hi folks,
> >
> > New blog posts:
> >
> > http://chintak.github.io/2013/08/texture-synthesis-efros-and-leung-algo/
> >
> > http://chintak.github.io/2013/09/texture-and-structural-inpainting/
> >
> > A
> > ny feedback welcome.
>
> It looks impressive.
> I wonder how it compares to the resynthetizer plugin in GIMP.
> Because I just tested Resynthetize this morning on diffraction images
> where pieces were missing and the results were disappointing.
>
> Indeed my problem is strange as I am looking for contiguous regions
> with a camera containing many holes (about 10%) and most algorithm
> fail on those image due to those holes.
>
> Cheers.
>
> --
> Jerome Kieffer <google at terre-adelie.org>
>
> --
> You received this message because you are subscribed to the Google Groups
> "scikit-image" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to scikit-image+unsubscribe at googlegroups.com.
> For more options, visit https://groups.google.com/groups/opt_out.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/scikit-image/attachments/20130905/036d3939/attachment.html>