Analysis of the Hand Motion Trajectories for Recognition of Air-Drawn Symbols

This paper presents a framework to recognize the symbols drawn in air using bare hand motion. The work marks a step towards development of non-tactile interfaces requiring no physical means for writing or drawing. To overcome the limitations of traditional two dimensional camera based acquisition, a preliminary step in gesture recognition, depth based sensor is used to acquire trajectory signals. In place of DTW (Dynamic Time Warp) and HMM (Hidden Markov Model) a non-time-warping approach is adopted in this work to recognize trajectories. Start and end delimitation of character trajectory drawing is established through finger detection based control gestures. Three simple features are evaluated by rule based and distance based classification, and classifier votes determine the recognition decision. Recognition accuracy up to 96% is achieved.