Recent Developments in the Study of Rapid Human Movements with the Kinematic Theory
La Théorie Cinématique des Mouvements Humains Rapides: Développements Récents
OPEN ACCESS
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:modelsrelying 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.
Résumé
Lorsqu'employée en reconnaissance des formes,la modélisation des mouvements humains vise,entre autres, à procurer certaines assises théoriques au traitement en ligne de l'écriture manuscrite et à fournir des connaissances fondamentales pouvant servir de balises dans la conception de systèmes automatiques. À ce jour,plusieurs approches ont été proposées pour modéliser la production des mouvements en général et de l'écriture en particulier:des modèles dynamiques,psychophysiques,cinématiques,à base de réseaux de neurones ou reposant sur des principes de minimisation. Parmi les modèles dits analytiques,la Théorie Cinématique et son équation delta-lognormale se sont avérées des plus prometteuses. Mais,bien qu'il ait été démontré que ce paradigme permettait de prendre en compte la majorité des phénomènes couramment observés en motricité fine,plusieurs problèmes théoriques et techniques ont retardé l'intégration directe ou indirecte de cette théorie dans la conception de systèmes. Dans cet article,nous faisons le point sur ces différentes difficultés et nous dévoilons les résultats de récents travaux que notre équipe a réalisés pour les surmonter. Dans un premier temps,dans une perspective de généralisation,nous présentons les principaux modèles de types log-normaux. Ensuite,du point de vue pratique,nous décrivons deux nouveaux algorithmes d'extraction de paramètres. Nous montrons également comment la nouvelle représentation qui en résulte peut être employée pour améliorer le traitement des signaux électromyographiques,ouvrant ainsi la porte à de nouvelles applications en génie biomédical. Nous concluons en présentant brièvement d'autres applications potentielles qui sont présentement en cours de développement dans notre laboratoire ou le seront dans un avenir rapproché.
Lognormals,Kinematic Theory,human movements,handwriting,signatures,neuromuscular networks,parameter estimation,electromyography.
Mots clés
Lognormales,Théorie Cinématique,mouvements humains,écriture,signatures,réseaux neuromusculaires, estimation de paramètres,électromyographie.
[1] M.A. ALIMI (2003), Beta neuro-fuzzy systems, in: W. Duch, D. Rutkowska (Eds.), TASK Quarterly J., Special Issue on Neural Networks, vol. 7(1), pp. 23-41.
[2] M.A.ALIMI, R. PLAMONDON (1996), A comparative study of speed/accuracy tradeoffs formulations: the case of spatially constrained movements where both distance and spatial precision are specified. In Handwriting and drawing research: basic and applied issues M. L. Simner, G.Thomassen,A.J.T.W.M., Ed. Amsterdam.
[3] M.A. ALIMI (1995), Contribution au développement d’une théorie de génération de mouvements simples et rapides: application au manuscrit, Thèse de Doctorat en Génie Électrique. École Polytechnique de Montréal.
[4] E. BIZZI, N. HOGAN, F.A. MUSSA-IVALDI, S. GISZTER (1992), Does the nervous system use equilibrium-point control to guide single and multiple joint movements?, Behav. Brain Sci. vol. 15, pp. 603613.
[5] E. BIZZI, P. DEV, P. MORASSO, and A. POLIT (1978), Effect of Load Disturbances During Centrally Initiated Movements, Journal of Neurophysiology, vol. 41, pp. 542-556.
[6] D. BULLOCK, S. GROSSBERG (1988), The VITE model: a neural command circuit for generating arm and articulator trajectories, in: J.A.S. Kelso,A.J. Mandell, M.F. Shlesinger (Eds.), Dynamic Patterns in Complex Systems, World Scientific Publishers, Singapore, pp. 305-326.
[7] P. CARRIÈRES et R. PLAMONDON (1994), An interactive Handwriting Teaching Aid, dans Advances in Handwriting and Drawing: A Multidisciplinary Approach, C. Faure, G. Lorette, A. Vinter, P. Keuss (Eds), Europia, Paris, 1994, p. 207-239.
[8] A. C. COHEN and B. J. Whitten (1980), Estimation in the ThreeParameter Lognormal Distribution, Journal of the American Statistical Association, vol. 75(370), pp. 399-404.
[9] E. L. CROW and K. SHIMIZU (eds.), (1988), Lognormal distributions: theory and applications, vol. 88, Dekker.
[10] J.J DENIER VAN DER GON. and J.P.H. THURING (1965), The guiding of human movements, Kybernetik, 14,145-148.
[11] S. DJEZIRI, W. GUERFALI, R. PLAMONDON, J.M. ROBERT (2002), Learning Handwriting with Pen Based Systems: Computational Issues, Pattern Recognition vol. 35(5), pp. 1049-1057.
[12] M. DJIOUA, R. PLAMONDON (2009),A New Algorithm and System for the Characterization of Handwriting Strokes with DeltaLognormal Parameters, IEEE Transactions on Pattern Analysis and Machine Intelligence, 30 Oct 2008. IEEE computer Society Digital Library. IEEE Computer Society <http://doi.ieeecomputersociety.org/10.1109/TPAMI.2008.264>
[13] M. DJIOUA, R. PLAMONDON (2008a), A New Methodology to Improve Myoelectric Signal Processing Using Handwriting, ICFHR’2008, pp. 112-117.
[14] M. DJIOUA, R. PLAMONDON (2008b),An interactive system for the automatic generation of huge handwriting databases from a few specimens, Pattern Recognition, 2008. ICPR 2008. 19th International Conference, pp. 1-4.
[15] M. DJIOUA (2007), “Contributions à la généralisation, à la compréhension et à l’utilisation de la Théorie Cinématique dans l’analyse et la synthèse du mouvement humain,” Thèse de Doctorat en Génie Électrique, École Polytechnique de Montréal, 380 pages.
[16] M. DJIOUA, R. PLAMONDON, A. DELLA CIOPPA and A. MARCELLI (2007), Deterministic and evolutionary extraction of Delta-Lognormal parameters: performance comparison, International Journal of Pattern Recognition and Artificial Intelligence, vol. 21(1), pp. 21-41.
[17] E.H. DOOIJES (1983), Analysis of handwriting movements, Acta Psychologica, vol. 54, pp. 99-114.
[18] S. EDELMAN, T. FLASH (1987),A model of handwriting, Biological Cybernetics, vol. 57, pp. 25-36.
[19] M. EDEN (1962), Handwriting and Pattern Recognition, IRE Trans. Inform. Theory, vol 8, pp. 160-166.
[20] J. D. ENDERLE and J. W. WOLFE (1987), Time-optimal control of saccadic eye movements, IEEE Transactions on Biomedical Engineering, vol. 34, pp. 43-55.
[21] S.E. ENGELBRECHT (2001), Minimum principles in motor control, J. Math. Psychol. vol. 45, pp. 497-542.
[22] A. G. FELDMAN (1966), Functional tuning of the nervous system with control of movement or maintenance of a steady posture. II. Controllable parameters of the muscle, Biophysics, vol. 11, pp. 565578.
[23] A.G. FELDMAN, M.L. LATASH (2005), Testing hypotheses and the advancement of science: recent attempts to falsify the equilibrium point hypothesis, Exp. Brain Res. vol.161 (1), pp. 91-103.
[24] C. FENG, A. WOCH and R. PLAMONDON (2002), “A Comparative Study of Two Velocity Profile Models for Rapid Stroke Analysis,” Proceedings of the 16th International Conference on Pattern Recognition, Quebec, Canada, vol. 4, pp. 52-55.
[25] T. FLASH and N. HOGAN (1985),The coordination of Arm Movements: An experimentally confirmed mathematical model, The Journal of Neuroscience, vol. 5, pp. 1688-1703.
[26] C. FLEISCHER, A. WEGE, K. KONDAK and G. HOMMEL (2006), Application of EMG signals for controlling exoskeleton robots, Biomedical Technology, vol.51, pp. 314-319.
[27] G. GANGADHAR, D. JOSEPH, V.S. CHAKRAVARTHY (2007), An oscillatory neuromotor model of handwriting generation, Int. J. Doc. Analyses and Recognition, vol.10 (2), pp. 69-84.
[28] S. GROSSBERG, R.W. PAINE (2000),A neural model of corticocerebellar interactions during attentive imitation and predictive learning of sequential handwriting movements, Neural Network, vol. 13, pp. 999-1046.
[29] W. GUERFALI (1996), Modèle Delta-lognormal vectoriel pour l’analyse du mouvement et la génération de l’écriture manuscrite,Thèse de Doctorat en génie électrique, École Polytechnique de Montréal.
[30] W. GUERFALI et R. PLAMONDON (1995a), Signal processing for the Parameter Extraction of the Delta Lognormal Model, In C. Archibald and P. Kwok (eds.): Research in Computer and Robot Vision. Singapore: World Scientific Publishing Co., pp. 217-232.
[31] W. GUERFALI et R. PLAMONDON (1995b), The Delta-Lognormal Theory for the Generation and Modelling of Cursive Characters, dans Proc. 3rd International Conference on Document Analysis and Recognition, Montréal, Canada, 14-16 Août 1995, pp. 495-498.
[32] C.M. HARRIS, D.M. WOLPERT (1998), Signal-dependent noise determines motor planning, Nature 394, pp. 780-784.
[33] H. HERMES and J. P. LASALLE (1969), Functional analysis and time optimal control. New York.
[34] P. W. HODGES and B. H. BUI (1996), A comparison of computerbased methods for the determination of onset of musclecontraction using electromyography, Electroencephalogr. Clin. Neurophysiol. vol. 101, pp. 511-519.
[35] N. HOGAN (1984), “An organization principle for a class of voluntary movements,” The Journal of Neurosciences, vol. 4, pp. 2745-2754.
[36] J.M. HOLLERBACH (1981), An oscillation theory of handwriting, Biological Cybernetics vol. 39 (2), pp. 39-156.
[37] K.T. KALVERAM (1998), A neural oscillator model learning given trajectories, or how an allo-imitation algorithm can be implemented into a motor controller, in: J.P. Piek (Ed.), Motor Behavior and Human Skill: A Multidisciplinary Approach, Human Kinetics, pp. 127-140.
[38] S. KELSO (1995), Dynamic patterns: The self-organization of brain and behavior, MIT Press, Cambridge, MA. USA.
[39] M.K. LANDOU (2008), Potentiels évoqués associés au temps d’occurrence du modèle Delta-Lognormal pour un mouvement volontaire induit, Mémoire de maîtrise, École Polytechnique de Montréal.
[40] LECLERC F., PLAMONDON R., LORETTE G. (1992), Des gaussiennes pour la modélisation des signatures et la segmentation des tracés manuscrits, Traitement du Signal 9, 347-358.
[41] G. LORETTE (1999), Handwriting Recognition or Reading? What is the Situation at the Dawn of the Third Millenium?, Int. J. Doc. Analysis and Recognition, vol.2(2), pp. 2-12.
[42] F.J. MAARSE (1987), The Study of Handwriting Movement: Peripheral Models and Signal Processing Tehcniques, Swets & Zertlinger, Lisse, The Netherlands.
[43] D. W. MARQUARDT (1963), An algorithm for least-squares estimation of non-linear parameters, Journal of the Society of Industrial and Applied Mathematics, vol. 11, pp. 431-441.
[44] P. MORASSO, F.A. MUSSA IVALDI (1982), Trajectory Formation and Handwriting: a Computational Model, Biological Cybernetics, vol 45, pp. 131-142.
[45] P. MORASSO, V. SANGUINETI, T. TSUJI (1994), A model for the Generation of Virtual Targets in Trajectory Formation, in Advances in Handwriting & Drawing: a Multidisciplinary Approach, C. Faure, P. Keuss, G. Lorette,A. Vinter, Eds. Europia, Paris.
[46] P.D. NEILSON, M.D. NEILSON (2005), An overview of adaptive model theory: solving the problems of redundancy, resources and nonlinear interactions in human movement control, J. Neural Eng. vol.2 (3), pp. 279-312.
[47] P.D. NEILSON (1993), The problem of redundancy in movement control:the adaptive model theory approach,Psychol. Res. vol.55,pp. 99-106.
[48] W.L. NELSON (1983), Physical principles for economies of skilled movements, Biological. Cybernetics vol. 46, pp. 135-147.
[49] C. O’REILLY, R. PLAMONDON (2007), A software assistant for the design and analysis of neuromuscular tests, Proc. IEEE Biomedical Circuits and Systems Conference, pp. 107-110.
[50] C. O’REILLY, R. PLAMONDON (2009), Development of a SigmaLognormal representation for on-line signatures. Pattern Recognition, 42(12), 3324-3337.
[51] C. O’REILLY, R. PLAMONDON, L.-H. LEBRUN, B. CLÉMENT, and P.A. MATHIEU (2009), Sigma-Lognormal Analysis of a Complex Movements Neuromuscular Test. To be presented at the 14th Conference of the International Graphonomics Society, Dijon, France.
[52] R. PLAMONDON, M.K. LANDOU, B. STEMMER (2009) Experimental observation of a new ERP signal, as predicted by the Kinematic Theory of rapid human movements, Neuroscience 2009, Chicago, 17-21 oct, abstract.
[53] R. PLAMONDON, C. FENG, and M. DJIOUA (2008), A kinematic theory of rapid human movement. Part V: The convergence of a neuromuscular response towards a lognormal, from theory to practice, École Polytechnique de Montréal, EPM/RT-2008-08, 37p.
[54] R. PLAMONDON and X. LI, M. DJIOUA (2007), Extraction of deltalognormal parameters from handwriting strokes, Journal of Frontiers of Computer Science in China, vol.1(1), pp. 106-113.
[55] R. PLAMONDON and M. DJIOUA (2006), “A multi-level representation paradigm for handwriting stroke generation” Human Movement Science, vol. 25, pp. 586-607.
[56] R. PLAMONDON, C. FENG, and A. WOCH (2003), A kinematic theory of rapid human movement. Part IV: a formal mathematical proof and new insights, Biological Cybernetics, vol. 89, pp. 126-138.
[57] R. PLAMONDON and W. GUERFALI (1998), The generation of handwriting with delta-lognormal synergies, Biological Cybernetics, vol. 78, pp. 119-132.
[58] R. PLAMONDON (1998), A kinematic theory of rapid human movements. Part III, Kinetic outcomes, Biological Cybernetics, vol. 78, pp. 133-145.
[59] R. PLAMONDON and A. ALIMI (1997), Speed/Accuracy tradeoffs in target-directed movements,Behavioral and Brain Sciences, vol. 20, pp. 279-349.
[60] R. PLAMONDON (1995a),A kinematic theory of rapid human movements. Part I. Movement representation and generation, Biological Cybernetics. vol.72 (4), pp. 295-307.
[61] R. PLAMONDON (1995b),A kinematic theory of rapid human movements. Part II. Movement time and control, Biological Cybernetics vol.72 (4), pp. 309-320.
[62] R. PLAMONDON et C.M. PRIVITERA (1995), A neural Model for Generating and Learning a Rapid Movement Sequence, Biological Cybernetics, vol. 74, no. 2, pp.117-130.
[63] R. PLAMONDON, A. M. ALIMI, P. YERGEAU, and F. LECLERC (1993), Modelling velocity profiles of rapid movements: a comparative study. Biological cybernetics. vol 69, pp.119-128.
[64] R. PLAMONDON, F. LAMARCHE (1986), Modelization of Handwriting: A System approach, in Graphonomics: Contemporary Research in Handwriting, H.S.R. Kao, G.P. van Galen and R. Hoosain, Eds. Elsevier,Amsterdam. pp. 169-183.
[65] V. POTKONJAK (2005), Robotic handwriting, International Journal of Humanoid Robotics, vol. 2, pp. 105-124.
[66] L.R.B. SCHOMAKER (1991), Simulation and recognition of handwriting movement: a vertical approach to modeling human motor behavior, PhD Thesis, Nijmegen University, Netherlands, 1991. [67] R.A. SCHMIDT, T.D. LEE, (1999) Motor Control and Learning: A behavioral Emphasis, 3rd Ed, Human Kinetics, Champaign Illinois, 493 pages.
[68] H. TANAKA, J.W. KRAKAUER, N. QIAN (2006), An optimization principle for determining movement duration, J. Neurophysiol. vol.95, pp. 3875-3886.
[69] A.J.W.M. THOMASSEN, P.J.G. KEUSS, and G.P. VAN GALEN (1983), Motor aspects of handwriting,Acta Psychologica, vol 54.
[70] Y. UNO, M. KAWATO, R. SUZUKI (1989), Formation, Control of optimal trajectory in human multijoint arm movement, Biological Cybernetics vol. 61, pp. 89-101.
[71] G.P. VAN GALEN and H.L.T. TEULINGS (1983), The independent monitoring of form and scale factors in Handwriting, Acta Psychologica in Motor Aspects of Handwriting, North Holland, Amsterdam, The Netherlands, vol. 54 pp. 9-22.
[72] Y. WADA, M. KAWATO (1995), A theory for cursive handwriting based on the minimization principle, Biological Cybernetics vol. 73 (1), pp. 3-13.
[73] M.E. WISE (1966), The geometry of lognormal and related distributions and an application to tracer-dilution curves, Statistica Neerlandica, vol. 20(1).
[74] A. WOCH (2006), Étude des primitives bidirectionnelles du mouvement dans le cadre de la Théorie Cinématique: confirmation expérimentale du modèle delta-lognormal, Thèse de Doctorat en Génie Électrique, École Polytechnique de Montréal.
[75] D.H. WOLPERT, W.G. MACREADY (1997), No Free Lunch Theorems for Optimization, IEEE Transactions on Evolutionary Computation, vol. 1(67).
[76] M. YASUHARA (1975), Experimental Studies on Handwriting, Process, Rep. Univ. Electro Comm. vol. 25, pp. 233-254. [77] P-G. ZANONE, S. ATHÈNES, I. SALLAGOITY and J.-M. ALBARET (2005), Switching Among Graphic Patterns is Governedby Coordination Dynamics of Handwriting,Proc. 12th Biennial Conf. of the Int. Graphonomics Society, Salerno, Italy, pp. 255-260.
[78] M. ZECCA, S. MICERA, M. C. CARROZZA, and P. DARIO (2002), Control of Multifunctional Prosthetic Hands by Processing the Electromyographic Signal, Critical Reviews in Biomedical Engineering, vol. 30(4-6), pp. 459-485.