Real-time Tracking of Multiple Fingertips and Its Applications for Augmented Desk Interface Systems

In this paper, we propose a fast and robust method for tracking multiple fingertips; we then demonstrate gesture recognition and an application based on measured fingertip trajectories for augmented desk interface systems. Our tracking method can track multiple fingertips reliably even in a complex background under a dynamically changing lighting condition with- out any markers. After multiple fingertips are detected in each input infrared image frame, correspondences of those fingertips between successive image frames are determined based on a prediction technique. Our gesture recognition system is particularly advantageous for Human-Computer Interaction (HCI) in that users can achieve interactions based on both symbolic gestures and direct manipulation with their own hands.