Example: Scikit-image and trackpy (bubble tracking in foams)
Hi, Just for your information, I wrote an example based on my research to show the use of scikit-image with trackpy for feature detection and tracking. http://nbviewer.ipython.org/github/soft-matter/trackpy-examples/blob/master/... Hopefully, this might be helpful for future workshops or presentations. Best, -- François Boulogne. http://www.sciunto.org GPG: 32D5F22F
Very nice example. Do we want to create a new page on the website with collections of nice iPython notebooks?
On Nov 20, 2014, at 1:05 PM, François Boulogne <fboulogne@sciunto.org> wrote:
Hi,
Just for your information, I wrote an example based on my research to show the use of scikit-image with trackpy for feature detection and tracking. http://nbviewer.ipython.org/github/soft-matter/trackpy-examples/blob/master/...
Hopefully, this might be helpful for future workshops or presentations.
Best,
-- François Boulogne. http://www.sciunto.org GPG: 32D5F22F
-- 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@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
Do we want to create a new page on the website with collections of nice iPython notebooks?
The problem would be to maintain this notebooks. I would rather advocate to cut the tutorials into shorter examples for the gallery (that can also be downloaded as notebooks), and to integrate the "best" notebooks into the user guide, to be sure that the code is maintained. But we could also have a list of links of nice notebooks hosted elsewhere. Just my 2 cents, Emma
Thanks for sharing, François--this is a great example of how well packages across the Python ecosystem function together. On 2014-11-20 21:27:56, Emmanuelle Gouillart <emmanuelle.gouillart@nsup.org> wrote:
Do we want to create a new page on the website with collections of nice iPython notebooks?
The problem would be to maintain this notebooks. I would rather advocate to cut the tutorials into shorter examples for the gallery (that can also be downloaded as notebooks), and to integrate the "best" notebooks into the user guide, to be sure that the code is maintained.
Also, we have the scikit-image-demos and skimage-tutorials repositories--it would fit in either, as long as it gets reworked to include the data. Stéfan
On 2014-11-20 21:27:56, Emmanuelle Gouillart <emmanuelle.gouillart@nsup.org> wrote:
Do we want to create a new page on the website with collections of nice iPython notebooks?
The problem would be to maintain this notebooks. I would rather advocate to cut the tutorials into shorter examples for the gallery (that can also be downloaded as notebooks), and to integrate the "best" notebooks into the user guide, to be sure that the code is maintained.
I think the guideline for now is to put examples with no additional dependencies in the gallery, and the rest in skimage-demos. Francois, it'd be fantastic to have this one in there as well. Stéfan
Francois, it'd be fantastic to have this one in there as well.
Sure ! :) -- François Boulogne. http://www.sciunto.org GPG: 32D5F22F
Hey everyone, I have looked into this one earlier and bookmarked it out of curiosity but the link François posted is no longer working Can i find this demo somewhere ? Much appreciated. On Friday, 28 November 2014 14:07:27 UTC+1, François Boulogne wrote:
Francois, it'd be fantastic to have this one in there as well.
Sure ! :)
-- François Boulogne. http://www.sciunto.org GPG: 32D5F22F
Le 25/03/2015 17:01, Georges H a écrit :
Hey everyone, I have looked into this one earlier and bookmarked it out of curiosity but the link François posted is no longer working Can i find this demo somewhere ?
The repository is there: https://github.com/soft-matter/trackpy-examples And you can also browse on this page: http://nbviewer.ipython.org/github/soft-matter/trackpy-examples/tree/master/... The one you are looking for is there: http://nbviewer.ipython.org/github/soft-matter/trackpy-examples/blob/master/... Best, -- François Boulogne. http://www.sciunto.org GPG: 32D5F22F
Very nice! I just tweeted about it :-). How good is that trackpy library? On Tuesday I was giving a presentation about scikit-image and someone in the audience asked me if I knew some good tools for 2D/3D + time image processing, for example for tracking particles/cells. I didn't know any, and actually I don't know whether there exist some "classical" and robust algorithms for particle tracking (like median filter for denoising, otsu thresholding, etc.), or if everything is very application-dependent. What is your experience about this? Best, Emmanuelle On Thu, Nov 20, 2014 at 01:05:24PM -0500, François Boulogne wrote:
Hi,
Just for your information, I wrote an example based on my research to show the use of scikit-image with trackpy for feature detection and tracking. http://nbviewer.ipython.org/github/soft-matter/trackpy-examples/blob/master/...
Hopefully, this might be helpful for future workshops or presentations.
Best,
Hi Emmanuelle, Le 20/11/2014 14:22, Emmanuelle Gouillart a écrit :
Very nice! I just tweeted about it :-).
:)
How good is that trackpy library? On Tuesday I was giving a presentation about scikit-image and someone in the audience asked me if I knew some good tools for 2D/3D + time image processing, for example for tracking particles/cells. I didn't know any, and actually I don't know whether there exist some "classical" and robust algorithms for particle tracking (like median filter for denoising, otsu thresholding, etc.), or if everything is very application-dependent. What is your experience about this?
I have a great experience and I warmly recommend the library. It's very easy to use, I'd say an investment of few hours to go through the tutorials and play a bit. The documentation is clear and the two mains steps (feature detection and feature tracking) are well separated. Trackpy provides an algorithm to detect particles, but you can also detect bubbles and probably cells if you write your own detection algorithm. Also, Trackpy smartly uses Pandas. Thus, it's very easy to manipulate the data and store everything in a h5 container. I had the occasion to meet Dan. The authors are very responsive and they are also on this ML afaik. I'm currently using trackpy for another project too. Best, -- François Boulogne. http://www.sciunto.org GPG: 32D5F22F
Great, thanks! It seems that most processing pipelines rely on first detecting objects of interest (eg with a segmentation step) and then tracking such objects. Do you know of any (generic-enough) approach that would perform both steps at the same time, ie if you know that the same objects must be found in several images this information can be used for performing the segmentation? On Thu, Nov 20, 2014 at 04:05:37PM -0500, François Boulogne wrote:
Hi Emmanuelle,
Le 20/11/2014 14:22, Emmanuelle Gouillart a écrit :
Very nice! I just tweeted about it :-).
:)
How good is that trackpy library? On Tuesday I was giving a presentation about scikit-image and someone in the audience asked me if I knew some good tools for 2D/3D + time image processing, for example for tracking particles/cells. I didn't know any, and actually I don't know whether there exist some "classical" and robust algorithms for particle tracking (like median filter for denoising, otsu thresholding, etc.), or if everything is very application-dependent. What is your experience about this?
I have a great experience and I warmly recommend the library. It's very easy to use, I'd say an investment of few hours to go through the tutorials and play a bit.
The documentation is clear and the two mains steps (feature detection and feature tracking) are well separated. Trackpy provides an algorithm to detect particles, but you can also detect bubbles and probably cells if you write your own detection algorithm. Also, Trackpy smartly uses Pandas. Thus, it's very easy to manipulate the data and store everything in a h5 container.
I had the occasion to meet Dan. The authors are very responsive and they are also on this ML afaik.
I'm currently using trackpy for another project too.
Best,
Le 20/11/2014 16:43, Emmanuelle Gouillart a écrit :
Great, thanks! It seems that most processing pipelines rely on first detecting objects of interest (eg with a segmentation step) and then tracking such objects. Do you know of any (generic-enough) approach that would perform both steps at the same time, ie if you know that the same objects must be found in several images this information can be used for performing the segmentation?
That's a good question. I'm not aware of such algorithm. It reminds me that machine learning could be eventually use also with trackpy. I opened a PR showing how scikit-image and scikit learn could be used together to detect digits: https://github.com/scikit-image/skimage-demos/pull/3 A similar procedure could be used in the situation of several populations of features with different shapes but similar sizes for instance (like a mixture of colloidal spheres and cubes) -- François Boulogne. http://www.sciunto.org GPG: 32D5F22F
On 20 November 2014 20:22, Emmanuelle Gouillart <emmanuelle.gouillart@nsup.org> wrote:
Very nice! I just tweeted about it :-).
How good is that trackpy library? On Tuesday I was giving a presentation about scikit-image and someone in the audience asked me if I knew some good tools for 2D/3D + time image processing, for example for tracking particles/cells. I didn't know any, and actually I don't know whether there exist some "classical" and robust algorithms for particle tracking (like median filter for denoising, otsu thresholding, etc.), or if everything is very application-dependent. What is your experience about this?
There are cell tracking specific softwares such as cell cognition (C++ + python). I think there are a lot of very specific software for cell tracking depending on what the data is. Cheers, N
Best, Emmanuelle
On Thu, Nov 20, 2014 at 01:05:24PM -0500, François Boulogne wrote:
Hi,
Just for your information, I wrote an example based on my research to show the use of scikit-image with trackpy for feature detection and tracking. http://nbviewer.ipython.org/github/soft-matter/trackpy-examples/blob/master/...
Hopefully, this might be helpful for future workshops or presentations.
Best,
-- 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@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
I like this example very much! Someone mentioned should you guys host a place to ipython notebooks of image processing? I think this would be a great idea. I posted a set of notebooks in the "Gallery of Interesting IPynbs" page, which does not have an image processing section. I had considered making one, but didn't want to step on any toes. There are so many notebooks on there now, that it probably would be better to have your own collection on scikit image. FYI here is the entry I put in the ipython notebook gallery of interesting notebooks: pyparty: Intuitive Particle Processing in Python <http://openresearchsoftware.metajnl.com/article/view/jors.bh>, Adam Hughes Notebook to Generate the Published Figures <http://nbviewer.ipython.org/github/hugadams/pyparty/blob/master/examples/Not...> | Also, check out the pyparty tutorial notebooks <https://github.com/hugadams/pyparty>. On Thursday, November 20, 2014 1:06:49 PM UTC-5, François Boulogne wrote:
Hi,
Just for your information, I wrote an example based on my research to show the use of scikit-image with trackpy for feature detection and tracking.
http://nbviewer.ipython.org/github/soft-matter/trackpy-examples/blob/master/...
Hopefully, this might be helpful for future workshops or presentations.
Best,
-- François Boulogne. http://www.sciunto.org GPG: 32D5F22F
Thanks François for an awesome tutorial! It was a very interesting read. And :+1: Adam's idea of hosting the skimage IPynbs somewhere. Stéfan, does skimage-demos live on the web anywhere? On Sat, Nov 22, 2014 at 5:36 AM, Adam Hughes <hughesadam87@gmail.com> wrote:
I like this example very much! Someone mentioned should you guys host a place to ipython notebooks of image processing? I think this would be a great idea. I posted a set of notebooks in the "Gallery of Interesting IPynbs" page, which does not have an image processing section. I had considered making one, but didn't want to step on any toes. There are so many notebooks on there now, that it probably would be better to have your own collection on scikit image. FYI here is the entry I put in the ipython notebook gallery of interesting notebooks: pyparty: Intuitive Particle Processing in Python <http://openresearchsoftware.metajnl.com/article/view/jors.bh>, Adam Hughes Notebook to Generate the Published Figures <http://nbviewer.ipython.org/github/hugadams/pyparty/blob/master/examples/Not...> | Also, check out the pyparty tutorial notebooks <https://github.com/hugadams/pyparty>. On Thursday, November 20, 2014 1:06:49 PM UTC-5, François Boulogne wrote:
Hi,
Just for your information, I wrote an example based on my research to show the use of scikit-image with trackpy for feature detection and tracking.
http://nbviewer.ipython.org/github/soft-matter/trackpy-examples/blob/master/...
Hopefully, this might be helpful for future workshops or presentations.
Best,
-- François Boulogne. http://www.sciunto.org GPG: 32D5F22F
-- 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@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
participants (8)
-
Adam Hughes -
Emmanuelle Gouillart -
François Boulogne -
Georges H -
Johannes Schoenberger -
Juan Nunez-Iglesias -
Nelle Varoquaux -
Stefan van der Walt