Abstract
Ten different feature vectors are tested in a gesture recognition task which utilizes 3D data gathered in real-time from stereo video cameras, and HMMs for learning and recognition of gestures. Results indicate velocity features are superior to positional features, and partial rotational invariance is sufficient for good performance.
| Original language | English |
|---|---|
| Pages | 157-162 |
| Number of pages | 6 |
| State | Published - 1996 |
| Event | Proceedings of the 1996 2nd International Conference on Automatic Face and Gesture Recognition - Killington, VT, USA Duration: Oct 14 1996 → Oct 16 1996 |
Conference
| Conference | Proceedings of the 1996 2nd International Conference on Automatic Face and Gesture Recognition |
|---|---|
| City | Killington, VT, USA |
| Period | 10/14/96 → 10/16/96 |