Gesture Recognition Using Improved Hierarchical Hidden Markov Algorithm

In this paper, we will record the hand movements into the computer using hand held sensors and then recognize the gesture using the suggested algorithm. The main purpose of this research is to build a gesture recognition system that develops an easier and faster recognition algorithm. To build the recognition model, we combine the hierarchical hidden Markov model (HHMM) to represent gesture units. In terms of hardware, we obtain the acceleration of hand movement by using inertial measurement unit (IMU). In terms of software, we use the improved algorithm to decide which gesture the movement belongs to. In the experiment, we sampled the ten Arabic numerals as our recognition objects. When the user waves the IMU sensor, the computer obtains the acceleration values of X, Y axes. And, the recognition program will acknowledge which Arabic numeral is being drawn.