Content-Aware Image Resizing

[Gabriel Landini]

I found this news in /. on a very interesting method:
http://science.slashdot.org/article.pl?sid=07/08/25/1835256&from=rss

There is even a video demo here:
http://www.youtube.com/watch?v=vIFCV2spKtg

Quite impressive!

Cheers

Gabriel

[Kenneth Sloan-2]

On Aug 26, 2007, at 6:06 AM, Gabriel Landini wrote:

> I found this news in /. on a very interesting method:
> http://science.slashdot.org/article.pl?sid=07/08/25/1835256&from=rss
>

yes, I saw the talk and demo at SIGGRAPH.  It *is* very impressive -  
but I suspect
it's also a bit dangerous for the applications that most people here  
have.  In particular, virtually all quantitative information goes  
right out the window.

If you were to publish an image that had been processed in this way,  
it would require a *serious* disclaimer!

--
Kenneth Sloan                                          
[hidden email]
Computer and Information Sciences                        [phone]
University of Alabama at Birmingham              FAX [phone]
Birmingham, AL 35294-1170                http://www.cis.uab.edu/sloan/

[Kenneth Sloan-2]

I'm considering running a graduate CS course in image processing with  
an emphasis on biological (microscopic and the like) images.

Is there concensus on a good textbook?

I'm familiar with most of the standard image processing/computer  
vision texts, but I'm fairly ignorant of those that are "ImageJ aware".

All suggestions welcome.

--
Kenneth Sloan                                          
[hidden email]
Computer and Information Sciences                        [phone]
University of Alabama at Birmingham              FAX [phone]
Birmingham, AL 35294-1170                http://www.cis.uab.edu/sloan/

[Yan Deng]

Try this one:

http://www.amazon.com/Digital-Image-Processing-Algorithmic-Introduction/dp/1846283795/ref=sr_1_2/002-6227502-5429616?ie=UTF8&s=books&qid=1188152460&sr=1-2

> I'm considering running a graduate CS course in image processing with
> an emphasis on biological (microscopic and the like) images.
>
> Is there concensus on a good textbook?
>
> I'm familiar with most of the standard image processing/computer
> vision texts, but I'm fairly ignorant of those that are "ImageJ aware".
>
> All suggestions welcome.
>
> --
> Kenneth Sloan
> [hidden email]
> Computer and Information Sciences                        [phone]
> University of Alabama at Birmingham              FAX [phone]
> Birmingham, AL 35294-1170                http://www.cis.uab.edu/sloan/
>

[Barthel, Kai Uwe]

During the last semester my students produced video podcasts of my  
course concerning the basics of image processing (using Photoshop and  
ImageJ). Perhaps this might help you to set up your course, however  
my course was taught in German.

You can find this podcast using Itunes
http://phobos.apple.com/WebObjects/MZStore.woa/wa/viewPodcast?
id=252560499

or on my website:
http://www.f4.fhtw-berlin.de/people/barthel/veranstaltungen/SS07/ 
Mete1/mete1.htm

Best regards
Kai

________________________________________
Prof. Dr.-Ing. Kai Uwe Barthel
Internationale Medieninformatik
FHTW Berlin, FB4, Treskowallee 8, 10313 Berlin
Tel: [phone]    Fax: [phone]
mailto:[hidden email]
http://www.f4.fhtw-berlin.de/~barthel


Am 26.08.2007 um 15:46 schrieb Kenneth Sloan:
I'm considering running a graduate CS course in image processing with  
an emphasis on biological (microscopic and the like) images.

Is there concensus on a good textbook?

I'm familiar with most of the standard image processing/computer  
vision texts, but I'm fairly ignorant of those that are "ImageJ aware".

All suggestions welcome.

--
Kenneth Sloan                                          
[hidden email]
Computer and Information Sciences                        [phone]
University of Alabama at Birmingham              FAX [phone]
Birmingham, AL 35294-1170                http://www.cis.uab.edu/sloan/

[lechristophe]

The article in pdf is very slow to download from the Shamir's lab
(http://www.faculty.idc.ac.il/arik/)

if you're interested, I uploaded it here :

https://www.bio.espci.fr/upload/files/imret.pdf

Very nice algorithm indeed, unfortunately the authors don't distribute
any implementation of it (source code, soft...). I can't wait to see it
implemented in ImageJ !

Christophe

Gabriel Landini a écrit :

> I found this news in /. on a very interesting method:
> http://science.slashdot.org/article.pl?sid=07/08/25/1835256&from=rss
>
> There is even a video demo here:
> http://www.youtube.com/watch?v=vIFCV2spKtg
>
> Quite impressive!
>
> Cheers
>
> Gabriel
>

[dscho]

Hi,

On Sun, 26 Aug 2007, Gabriel Landini wrote:

> I found this news in /. on a very interesting method:
> http://science.slashdot.org/article.pl?sid=07/08/25/1835256&from=rss
>
> There is even a video demo here:
> http://www.youtube.com/watch?v=vIFCV2spKtg
>
> Quite impressive!

I put up a crude implementation on

        http://wbgn013.biozentrum.uni-wuerzburg.de/ImageJ/seam-remover.html

It is not very flexible yet: handles only ColorProcessors, and the only
energy it ever looks at is the sum of the x- and y-derivatives.  (Patches
welcome...)

Ciao,
Dscho

[Ben Woodcroft-2]

Cool!

Thanks, worked for me - I was able to downsize an image. The output image
wasn't pretty, but that's because it was a face.

Be nice to have upsizing going as well, but I'm not complaining. Thanks!

ben

On 9/1/07, Johannes Schindelin <[hidden email]> wrote:

>
> Hi,
>
> On Sun, 26 Aug 2007, Gabriel Landini wrote:
>
> > I found this news in /. on a very interesting method:
> > http://science.slashdot.org/article.pl?sid=07/08/25/1835256&from=rss
> >
> > There is even a video demo here:
> > http://www.youtube.com/watch?v=vIFCV2spKtg
> >
> > Quite impressive!
>
> I put up a crude implementation on
>
>
> http://wbgn013.biozentrum.uni-wuerzburg.de/ImageJ/seam-remover.html
>
> It is not very flexible yet: handles only ColorProcessors, and the only
> energy it ever looks at is the sum of the x- and y-derivatives.  (Patches
> welcome...)
>
> Ciao,
> Dscho
>

[NeLaS]

Hello,

same here, it worked for me when downsizing a desktop screenshot! The final
result was good except for the inferior panel where the content and words
got a little bit clumped - I changed width from 1280 to 800 pixels. The main
content had very little distortions.

I have uploaded some shots at:

http://organelas.com/2007/08/31/seam-remover/

nice!

bruno

--
Bruno C. Vellutini
[organelas.com]

Centro de Biologia Marinha (CEBIMar)
Universidade de São Paulo
Av. Manoel H. do Rego km 131,5
11600-000 São Sebastião, SP, Brasil
http://www.usp.br/cbm/

On 9/1/07, Ben Woodcroft <[hidden email]> wrote:

>
> Cool!
>
> Thanks, worked for me - I was able to downsize an image. The output image
> wasn't pretty, but that's because it was a face.
>
> Be nice to have upsizing going as well, but I'm not complaining. Thanks!
>
> ben
>
> On 9/1/07, Johannes Schindelin <[hidden email]> wrote:
> >
> > Hi,
> >
> > On Sun, 26 Aug 2007, Gabriel Landini wrote:
> >
> > > I found this news in /. on a very interesting method:
> > > http://science.slashdot.org/article.pl?sid=07/08/25/1835256&from=rss
> > >
> > > There is even a video demo here:
> > > http://www.youtube.com/watch?v=vIFCV2spKtg
> > >
> > > Quite impressive!
> >
> > I put up a crude implementation on
> >
> >
> > http://wbgn013.biozentrum.uni-wuerzburg.de/ImageJ/seam-remover.html
> >
> > It is not very flexible yet: handles only ColorProcessors, and the only
> > energy it ever looks at is the sum of the x- and
> y-derivatives.  (Patches
> > welcome...)
> >
> > Ciao,
> > Dscho
> >
>