Quantized features for gesture recognition using high speed vision camera

In addition to speech, gestures have been considered as a means of interacting with a computer as naturally as possible. Like speech, gestures can be acquired and recognized using hidden Markov models (HMMs), but there are several problems that must be overcome. We propose solutions to two of these problems: the feature extraction and the HMMs training. First, the acquisition is done by means of a high speed vision camera which allows the position of a hand to be obtained every 1 ms. This simplifies the feature extraction task and also allows low-level fusion with speech to be considered, which is a future goal. Secondly, we introduce quantized features, after carefully selecting extracted features, in order to avoid drastically increasing the size of the gesture database needed for good training of the HMMs. We finally show results that demonstrate the ability of such quantized features to significantly improve the recognition rate despite a rather small database and to allow user-independent recognition of gestures.