Parametric Hidden Markov Models for Gesture Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
W4: Who? When? Where? What? A Real Time System for Detecting and Tracking People
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Real Time Recognition of Gesture and Gesture Degree Information Using Multi Input Image Sequence
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
ASL Recognition Based on a Coupling Between HMMs and 3D Motion Analysis
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
| Hi-index | 0.00 |
In this paper, we describe the method that can automatically compose gesture models and recognize those gestures using 2D features extracted from gesture image sequences. In the conventional gesture recognition algorithms, previously well-known patterns are introduced by the hand or the model indexing algorithm. However, our method automatically composes the model space by clustering arbitrary input image sequences. The models are recognized as gesture using probability calculation of HMM. Our method can compose the models fast and robustly and is easy to learn on new image sequences.