Multispectral random walker segmentation
Emmanuelle Gouillart
emmanuelle.gouillart at nsup.org
Mon Aug 27 08:55:11 EDT 2012
Hi Josh,
my changes have been merged, so if you pull from github they are in
the master branch now, you can add your changes and make a pull request!
Cheers,
Emmanuelle
On Thu, Aug 23, 2012 at 02:50:05PM -0700, Josh Warner wrote:
> I'd be happy to include your suggested changes, if it's simpler to go that
> route than have two separate pull requests. �I don't want to step on any
> toes regarding attribution, though. �
> Having the 'soft' probabilities available is definitely a useful
> improvement (cleanup, fuzzy post-processing), and I'm glad you implemented
> that! �
> Josh
> On Monday, August 20, 2012 4:11:45 PM UTC-5, Emmanuelle Gouillart wrote:
> Hi Josh,
> extending the random walker algorithm to multichannel images sounds like
> a very nice idea, and I'm sure that it would be useful for other people
> (including myself!).
> In fact, I had started working on some improvements of the random walker
> code but didn't go as far as proposing the pull request. I have a branch
> for that on
> [1]https://github.com/emmanuelle/scikits.image/tree/fix_random_walker,
> maybe
> you can include these changes when you contribute your changes?
> Cheers,
> Emmanuelle
> On Mon, Aug 20, 2012 at 10:03:53AM -0700, Josh Warner wrote:
> > � �I have modified the existing random walker algorithm into a fully
> > � �backwards-compatible version which allows inclusion of
> multispectral data,
> > � �e.g. RGBA channels or different (registered) image modalities. �I
> really
> > � �liked the existing algorithm, so I just extended it rather than
> write one
> > � �from scratch for my own purposes. �The overhead is minimal;
> multispectral
> > � �processing is triggered if data is passed as an iterable of arrays
> rather
> > � �than just an array. �
> > � �This amounts to combining image gradients as sqrt(sum-of-squares)
> and
> > � �dividing by sqrt(#channels). �For obvious reasons, the several
> channels
> > � �must be pre-processed to have data on similar ranges by whitening
> or a
> > � �similar method. �Not usually a problem for RGB, but in medical
> imaging
> > � �this rears its head.
> > � �Would this be of interest to the community? �I'd be happy to
> contribute
> > � �the changes if there is interest.
> References
> Visible links
> 1. https://github.com/emmanuelle/scikits.image/tree/fix_random_walker
More information about the scikit-image
mailing list