Development of gesture database for an adaptive gesture recognition system

Abstract

The application of human gesture for the interaction between humans and computers is becoming an impressive alternative. Particularly, hand gesture is used as a non-verbal communication between human and machines. Most of recent studies for gesture recognition deal with the shape and movement of hands and also discussion on factor that contributed to the effect of individual factors in arm motions. This paper mainly concentrated on the development of a gesture database to eliminate individual factors, which affect the efficiency of the recognition system. An adaptive gesture recognition system is proposed, and the system could adaptively select the correspond database for the purpose of comparison with the input gesture. A classification algorithm is introduced to investigate whether the individual factor is the primary cause that affects the efficiency of the recognition system. In this study, by examining the characteristics of hand trajectories, motion features are selected and classified by using a statistical approach. The result shows that the individual factor, affects the efficiency of the recognition system. Moreover, the body structure of the performer needs to be considered in the development of the gesture database.