Bayesian Action-Perception Computational Model: Interaction of Production and Recognition of Cursive Letters

Abstract : In this paper, we study the collaboration of perception and action representations involved in cursive letter recognition and production. We propose a mathematical formulation for the whole perception-action loop, based on probabilistic modeling and Bayesian inference, which we call the Bayesian Action-Perception (BAP) model. Being a model of both perception and action processes, the purpose of this model is to study the interaction of these processes. More precisely, the model includes a feedback loop from motor production, which implements an internal simulation of movement. Motor knowledge can therefore be involved during perception tasks. In this paper, we formally define the BAP model and show how it solves the following six varied cognitive tasks using Bayesian inference: i) letter recognition (purely sensory), ii) writer recognition, iii) letter production (with different effectors), iv) copying of trajectories, v) copying of letters, and vi) letter recognition (with internal simulation of movements). We present computer simulations of each of these cognitive tasks, and discuss experimental predictions and theoretical developments.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00645868
Contributor : Julien Diard <>
Submitted on : Monday, November 28, 2011 - 5:20:42 PM
Last modification on : Thursday, July 11, 2019 - 2:10:06 PM
Long-term archiving on : Monday, December 5, 2016 - 8:20:24 AM

Files

gilet11.pdf
Publisher files allowed on an open archive

Identifiers

Collections

Citation

Estelle Gilet, Julien Diard, Pierre Bessiere. Bayesian Action-Perception Computational Model: Interaction of Production and Recognition of Cursive Letters. PLoS ONE, Public Library of Science, 2011, 6 (6), pp.e20387. ⟨10.1371/journal.pone.0020387⟩. ⟨hal-00645868⟩

Share

Metrics

Record views

551

Files downloads

393