Pattern recognition using temporal fuzzy automata
In this paper, we propose a syntactic pattern recognition approach based on fuzzy automata, which can cope with the variability of patterns by defining imprecise models. This approach is called temporal fuzzy automata as it allows the inclusion of time restrictions to model the duration of the different states. The concept of fuzzy state makes it possible to handle ambiguity as the automaton can be in several states at the same time. Another advantage of our approach is the capability to synchronize with the signal, which allows us to avoid the segmentation stage before the recognition process. Furthermore, a learning method based on dynamic time warping is provided that makes it possible to automatically generate models. Finally, to demonstrate the performance and robustness of this approach, we have applied it to the recognition of hand gestures without any kind of signal preprocessing.