Building Temporal Models for Gesture Recognition

This work presents a piecewise linear approximation to non-linear Point Distribution Models for modelling the human hand. The work utilises the natural segmentation of shape space, inherent to the technique, to apply temporal constraints which can be used with CONDENSATION to support multiple hypotheses and quantum leaps through shape space. This paper presents a novel method by which the one-state transitions of the English Language are projected into shape space for tracking and model prediction using a HMM like approach. 1 Introduction Previous work by the author and other researchers have investigated statistical models of deformation 1-8. These deformable models have been used to learn a priori shape and deformation from a training set of examples which, represent the shape and deformation of an object or a class of objects. Models are typically constructed that know what is valid deformation but not when deformation is valid. This important temporal constraint is benef...