A Method for Selection of Optimal Hand Gesture Vocabularies

This work presents an analytical approach to design a gesture vocabulary (GV) using multiobjectives for psycho-physiological and gesture recognition factors. Previous works dealt only with selection of hand gestures vocabularies using rule based or ad-hoc methods. The analytical formulation in our research is a demonstration of the future need defined by previous research. A meta-heuristic approach is taken by decomposing the problem into two sub-problems: (i) finding the subsets of gestures that meet a minimal accuracy requirement, and (ii) matching gestures to commands to maximize the human factors objective. The result is a set of solutions from which a Pareto optimal subset is selected. An example solution from the Pareto set is exhibited using prioritized objectives.