A Proposal of Pattern Space Trajectory for Gesture Spotting Recognition

We propose a new appearance-based feature for real-time gesture recognition from motion images. The feature is the shape of the trajectory caused by human gestures, in the "Pattern Space" defined by the inner-product between patterns on frame images. It has three advantages, 1) it is invariant in term of the target human's position, size and lie, 2) it allows gesture recognition without interpreting frame image contents and 3) there is no costly statistical calculation involved. In this paper, we describe the properties of the gesture trajectory feature, and some experimental results in order to show its applicability to gesture recognition.