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 overfitting to sequences of incorrect categories is restricted. The proposed method exhibited high recognition accuracy in finger-writing character recognition.

• Type: Conference
• Year: 2008
• Where: ICPR
• Authors: Hiroyuki Ishida, Tomokazu Takahashi, Ichiro Ide, Hiroshi Murase
• Keywords: Computer Vision, Finger-writing Character Recognition, ICPR 2008, Input Image Sequence, Reference Sequences