I’m trying to use DTW to detect gestures for all 10 fingers. I’ve built the models for 1 finger, but it seems that DTW doesn’t allow for multiple inputs. Does that mean I’ll have to have 10 parallel instances of wekinator running, one for each finger, even if they use the same model?
After I’m done with the fingers, I wanted to go to other gestures with hand palms, etc. If the answer to the previous question is no, that would mean that the number of instances working simultaneously will grow a lot.
DTW allows for multiple inputs — e.g., you could recognise a gesture made using all 10 fingers. However, it doesn’t allow for multiple parallel outputs — i.e., recognising a set of 5 gestures made with 1 finger, a set of 3 other gestures made with another finger, etc. You are correct that you’d need multiple instances of Wekinator running to implement this sort of thing, and if you’re recognising the same gestures then you could just load the same model into each one. However, due to the inefficiency of DTW you might find this *very* slow (and this wouldn’t change even if you could use the same model in a single project for each finger), so I’d recommend you think about another approach if you find this doesn’t work as accurately or quickly as you need.
I thought so, that it would lead to a big build-up of ressources when trying to work with a such detailed configuration. From my short experience, the wekinator is much more robust as other dtw objects, as it allows several models for the same gesture type – but it also means lots more ressources. Unfortunately I can’t say if there is something in the weka libraries that could be optimized for this, as I won’t be able to read them.
I’ll continue to see the different approaches and recheck what is desirable vs. what is possible.