Gesture Classification Using Hidden Markov Models and Viterbi Path Counting

Human-Machine interfaces play a role of growing importance as computer technology continues to evolve. Motivated by the desire to provide users with an intuitive gesture input system, our work presented in this paper describes a Hidden Markov Model (HMM) based framework for hand gesture detection and recognition. The gesture is modeled as a hidden Markov model. The observation sequence used to characterize the states of the HMM are obtained from the features extracted from the segmented hand image by Vector Quantization. In the recognition system, we try several different HMM models and training algorithms to find the algorithms with high recognition rate and low computational complexity.

• Type: Conference
• Year: 2003
• Where: DICTA
• Authors: Nianjun Liu, Brian C. Lovell
• Keywords: DICTA 2003, DICTA 2007, Gesture, Gesture Input System, Hidden Markov Model