Multispectral random walker segmentation

[Emmanuelle Gouillart]

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