Gesture Recognition Based on Elastic Deformation Energies

We present a method for recognizing gesture motions based on elastic deformable shapes and curvature templates. Gestures are modeled using a spline curve representation that is enhanced with elastic properties: the entire spline or any of its parts may stretch or bend. The energy required to transform a gesture into a given template gives an estimation of the similarity between the two. We demonstrate the results of our gesture classifier with a video-based acquisition approach.

• Type: Conference
• Year: 2007
• Where: GW
• Authors: Radu-Daniel Vatavu, Laurent Grisoni, Stefan Gheorghe Pentiuc
• Keywords: Biometrics, Elastic Deformable Shapes, Gesture, Gesture Motions, GW 2007