Bayesian Sensing Hidden Markov Model for Hand Gesture Recognition

This paper proposes a modified Bayesian Sensing Hidden Markov Model (BS-HMM) to address the problem of hand gestures recognition on few labeled data. In this work, BS-HMM is investigated based on its success to address the problem of large-vocabulary of continuous speech recognition. We introduced error modeling into BS-HMM basis vector to handle the noise that occurs in the data. We also introduced a forgetting factor to preserve important information from previous basis vector and to improve both convergence and representation ability of the BS-HMM basis vector. We modified Moving Pose method to extract the feature descriptor from hand gestures data. To evaluate the performance of our system, we compared our proposed method with previously proposed HMM methods. The experimental result showed the improvement of proposed method over others, even when only a small number of labeled data are available for training dataset.