Extracting Motion Primitives from Natural Handwriting Data

For the past 10 years it has become clear that biological movement is made up of sub-routine type blocks, or motor primitives, with a central controller timing the activation of these blocks, creating synergies of muscle activation. This paper shows that it is possible to use a factorial hidden Markov model to infer primitives in handwriting data. These primitives are not predefined in terms of location of occurrence within the handwriting, and they are not limited or defined by a particular character set. Also, the variation in the data can to a large extent be explained by timing variation in the triggering of the primitives. Once an appropriate set of primitives has been inferred, the characters can be represented as a set of timings of primitive activations, along with variances, giving a very compact representation of the character. Separating the motor system into a motor primitive part, and a timing control gives us a possible insight into how we might create scribbles on paper.

[1]  P. R. Davidson,et al.  Motor learning and prediction in a variable environment , 2003, Current Opinion in Neurobiology.

[2]  Emilio Bizzi,et al.  Combinations of muscle synergies in the construction of a natural motor behavior , 2003, Nature Neuroscience.

[3]  R. G. J. Meulenbroek,et al.  Adaptation of a reaching model to handwriting: How different effectors can produce the same written output, and other results , 1996, Psychological research.

[4]  Maja J. Mataric,et al.  Automated Derivation of Primitives for Movement Classification , 2000, Auton. Robots.

[5]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[6]  Robert A. Jacobs,et al.  Motor timing learned without motor training , 2000, Nature Neuroscience.

[7]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[8]  E. Bizzi,et al.  Book Review: Modular Organization of Spinal Motor Systems , 2002, The Neuroscientist : a review journal bringing neurobiology, neurology and psychiatry.

[9]  Daniel M. Wolpert,et al.  Internal models underlying grasp can be additively combined , 2004, Experimental Brain Research.

[10]  N. Mai,et al.  Visual control of automated handwriting movements , 1999, Experimental Brain Research.

[11]  D M Wolpert,et al.  Multiple paired forward and inverse models for motor control , 1998, Neural Networks.

[12]  Emilio Bizzi,et al.  Modular organization of motor behavior in the frog's spinal cord , 1995, Trends in Neurosciences.

[13]  Larry A Kramer,et al.  Neurobiology of perceptual and motor timing in children with spina bifida in relation to cerebellar volume. , 2004, Brain : a journal of neurology.

[14]  Emilio Bizzi,et al.  Shared and specific muscle synergies in natural motor behaviors. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[15]  Alan C. Evans,et al.  Cerebellar Contributions to Motor Timing: A PET Study of Auditory and Visual Rhythm Reproduction , 1998, Journal of Cognitive Neuroscience.

[16]  Eamonn J. Keogh,et al.  Probabilistic discovery of time series motifs , 2003, KDD '03.

[17]  Zoubin Ghahramani,et al.  Perspectives and problems in motor learning , 2001, Trends in Cognitive Sciences.

[18]  Samy Bengio,et al.  Offline cursive word recognition using continuous density hidden Markov models trained with PCA or ICA features , 2002, Object recognition supported by user interaction for service robots.

[19]  Michael I. Jordan,et al.  Factorial Hidden Markov Models , 1995, Machine Learning.

[20]  Michael I. Jordan,et al.  Optimal feedback control as a theory of motor coordination , 2002, Nature Neuroscience.

[21]  Thomas Eggert,et al.  Learning to write letters: transfer in automated movements indicates modularity of motor programs in human subjects , 2000, Neuroscience Letters.

[22]  W J Kargo,et al.  Rapid Correction of Aimed Movements by Summation of Force-Field Primitives , 2000, The Journal of Neuroscience.

[23]  David Barber,et al.  A generative model for music transcription , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[24]  Jun Nakanishi,et al.  Learning Movement Primitives , 2005, ISRR.