Weka training - apply same classifier to multiple stacks

[diyoyo]

Hi,
I cannot figure out a good way to use the Weka Segmentation tool in ImageJ.
Basically, I am missing at least two things, but maybe it is already doable (hence my post) :

1. How to save current ROIs assigned to one class or the other, and how to be able to resume my work later on…
2. How to Load a classifier, apply it to one stack of images, then apply it to another stack of images, without having to load it again ? It feels like the weka segmentation tool is assigned to one stack at a time,and everytime a new instance is created, which needs a full reload of the classifier. My classifier starts to be quite big and I don’t load to load it multiple times…

Thanks.

[etadobson (Ellen TA Dobson)]

@diyoyo

How to save current ROIs assigned to one class or the other, and how to be able to resume my work later on…

Check out this older thread on the subject (always a good idea to have a quick search through the forum):

[trainable weka segmentation 3D] How to save labels?

Any active trace in the Trainable Weka Segmentation can be added to the ROI Manager by pressing its Add [t] button or hitting T. After adding the trace to a class, you can click the entry in the trace list (e.g. trace 0) to activate it, and then add it to the ROI manager. Note that if the sole purpose is to keep the traced data for improving the training later (on the same or on a different image), you should use the Save data and Load data buttons in TWS.

How to Load a classifier, apply it to one stack of images, then apply it to another stack of images, without having to load it again ? It feels like the weka segmentation tool is assigned to one stack at a time,and everytime a new instance is created, which needs a full reload of the classifier. My classifier starts to be quite big and I don’t load to load it multiple times…

And again, here is another answer from an older thread:

Java script and Trainable Weka Segmentation

The Trainable Segmentation Scripting page has extensive documentation about how to use the plugin via scripting. The examples are in Beanshell, but it’s sufficiently similar to Javascript to learn from them. Something along these lines should get you started: // @ImagePlus imp importClass(Packages.trainableSegmentation.WekaSegmentation); var weka = WekaSegmentation( imp ); var classifierFile = "/path/to/your/classifier-file"; weka.loadClassifier(classifierFile); weka.applyClassifier(True);…

If these do not provide the exact answers you need in your case - reply here again. We are here to help!

[diyoyo]

Hi, thanks for this, indeed, I could have looked more deeply.
However, I was looking for an answer that would not require scripting (for using the same classifier) : isn’t there a way to keep the classifier in memory while opening Weka on another image? Or to keep the same Weka instance and open another image from that instance (without scripting)?
The way I would see it would be to be able to open the Weka even without any opened image, and open them directly from the weka interface.

As for precisions on my first question, I will directly write to the original thread, then.