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.
KeywordsHide State Muscle Synergy Motor Timing Primitive Activation Motor Primitive
Unable to display preview. Download preview PDF.
- 7.Dennis, M., Edelstein, K., Hetherington, R., Copeland, K., Frederick, J., Blaser, S.E., Kramer, L.A., Drake, J.M., Brandt, M., Fletcher, J.M.: Neurobiology of perceptual and motor timing in children with spina bifida in relation to cerebellar volume. Brain (2004)Google Scholar
- 10.Ijspeert, A., Nakanishi, J., Schaal, S.: Learning attractor lanscapes for motor primitives, vol. 15. MIT Press, Cambridge (2003)Google Scholar
- 11.Kargo, W.J., Giszter, S.F.: Rapid corrections of aimed movements by combination of force-field primitives. J. Neurosci. 20, 409–426 (2000)Google Scholar
- 12.Matarić, M.J.: Primitives-based humanoid control and imitation. Technical report, DARPA MARS project (2004)Google Scholar
- 15.Schaal, S.P., Nakanishi, J., Ijspeert, A.: Learning movement primitives. In: ISRR 2003 (2004)Google Scholar