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

Wow, that was quick :-), thanks! I'll have a look tomorrow, I'm just back from Brussels and Euroscipy! Emmanuelle On Mon, Aug 27, 2012 at 02:18:22PM -0700, Josh Warner wrote:

Pull request is up! �I also fixed a bug in the fallback call of _solve_cg() if pyamg is not installed. �Comments appreciated. Josh On Monday, August 27, 2012 7:55:11 AM UTC-5, Emmanuelle Gouillart wrote:

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][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. [2]https://github.com/emmanuelle/scikits.image/tree/fix_random_walker

References

Visible links 1. https://github.com/emmanuelle/scikits.image/tree/fix_random_walker 2. https://github.com/emmanuelle/scikits.image/tree/fix_random_walker

On Mon, Sep 17, 2012 at 3:09 PM, Josh Warner <silvertrumpet999@gmail.com> wrote:

I noticed a documentation inconsistency in `labels` for random_walker; it hadn't been updated with the rest of the file and still said `labels` should be the same shape as `data`. This is true for the single-channel case, but for multichannel input `labels` should look like a single channel (missing the final dimension in `data`). Proposed docfix is submitted in a PR.

Thanks, Josh! I merged your PR. Stéfan