A Framework to Plot and Recognize Hand Motion Trajectories towards Development of Non-tactile Interfaces

This work demonstrates a real time framework to recognize trajectories articulated in the air using bare hand motion. A frontend is established to plot the trajectories as well as to spot the interleaved dynamic gestures. Finger detection based controls and trajectory plotting velocity help to spot the gesture boundaries. Trajectories are described through a unique Equi-Polar Signature (EPS) derived from circular grid normalization of trajectory points. EPS is invariant to translation, scale, rotation and stroke directions. k-Nearest Neighbor (KNN) classification strategy recognizes EPSs of digits 0-9 and operator symbols ‘+’, ‘–’, ‘×’, and ‘/’. Unlike previous path alignment algorithms, the proposed EPS scheme executes in linear time and fits to real-time constraints. On a customized depth video dataset of 2280 trajectories, 94.1% recognition accuracy is achieved.