A facial gesture switch using hidden Markov models
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Emli-Mari Nel.
I will present a system that can identify a facial gesture based on duration information and optical flow features. There is a short training phase where the user is asked to make his/her gesture three times. A hidden Markov model is then used to identify the signal (gesture) by exploiting the fact that the user made the gesture three times. I will show preliminary results (including an example of a patient with locked-in syndrome using the system). This is still work in progress – suggestions will be more than welcome.
This talk is part of the Inference Group series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|