Recent Developments in the Study of Rapid Human Movements with the Kinematic Theory

Human movement modeling can be of great interest for the design of pattern recognition systems relying on the processing of fine neuromotricity, like on-line handwriting recognition, signature verification as well as in the design of intelligent systems involving in a way or another the processing of human movements. Among other things, this general approach aims at elaborating a theoretical background for any handwriting processing applications as well as providing some basic knowledge that can be integrated or taking care of in the development of automatic systems. So far, many models have been proposed to study human movement production in general and handwriting in particular: models relying on neural networks, dynamics models, psychophysical models, kinematic models and models exploiting minimization principles. Among the models which provide analytical representations, the Kinematic Theory of rapid human movements and its delta-lognormal model have been considered as very promising. However, although numerous studies have shown that such a paradigm could explain most of the basic phenomena constantly reported in classical studies dealing with fine motor control, many problems, both theoretical and technical, have postponed its direct or indirect integration in the design of pattern recognizers. In this paper, we overview these problems and report on various projects conducted by our team to overcome these difficulties. First, we present a brief recall of the different models in the field and focus on the family of models involving lognormal functions. Then, from a practical perspective, we describe two new parameter extraction algorithms suitable for the reverse engineering of single strokes as well as complex handwriting signals. We show how the resulting representation can be used to improve electromyographic signal processing, opening a windows on new applications for handwriting processing, particularly in biomedical engineering and in some fields of neurosciences. We briefly conclude by listing various potential applications of the Kinematic Theory, particularly in the fields of handwriting recognition, signature verification and biomedical signal processing.