A Hilbert warping method for camera-based finger-writing recognition

We propose a time-warping algorithm for recognizing finger actions by a camera. In the proposed method, an input image sequence is aligned to the reference sequences by phase-synchronization of the analytic signals, and then classified by comparing the cumulative distances. A major benefit of this method is that over-fitting to sequences of incorrect categories is restricted. The proposed method exhibited high recognition accuracy in finger-writing character recognition.