Limits...
A Bayesian computational model for online character recognition and disability assessment during cursive eye writing.

Diard J, Rynik V, Lorenceau J - Front Psychol (2013)

Bottom Line: Preliminary experimental results are presented, which illustrate the method, showing the feasibility of character recognition in the context of eye writing.We then show experimentally how a model of the unknown character can be used to detect trajectories that are likely to be new symbols, and how disability assessment can be performed by opportunistically observing characteristics of fine motor control, as letter are being traced.Experimental analyses also help identify specificities of eye writing, as compared to handwriting, and the resulting technical challenges.

View Article: PubMed Central - PubMed

Affiliation: Laboratoire de Psychologie et NeuroCognition, Université Grenoble Alpes-CNRS Grenoble, France.

ABSTRACT
This research involves a novel apparatus, in which the user is presented with an illusion inducing visual stimulus. The user perceives illusory movement that can be followed by the eye, so that smooth pursuit eye movements can be sustained in arbitrary directions. Thus, free-flow trajectories of any shape can be traced. In other words, coupled with an eye-tracking device, this apparatus enables "eye writing," which appears to be an original object of study. We adapt a previous model of reading and writing to this context. We describe a probabilistic model called the Bayesian Action-Perception for Eye On-Line model (BAP-EOL). It encodes probabilistic knowledge about isolated letter trajectories, their size, high-frequency components of the produced trajectory, and pupil diameter. We show how Bayesian inference, in this single model, can be used to solve several tasks, like letter recognition and novelty detection (i.e., recognizing when a presented character is not part of the learned database). We are interested in the potential use of the eye writing apparatus by motor impaired patients: the final task we solve by Bayesian inference is disability assessment (i.e., measuring and tracking the evolution of motor characteristics of produced trajectories). Preliminary experimental results are presented, which illustrate the method, showing the feasibility of character recognition in the context of eye writing. We then show experimentally how a model of the unknown character can be used to detect trajectories that are likely to be new symbols, and how disability assessment can be performed by opportunistically observing characteristics of fine motor control, as letter are being traced. Experimental analyses also help identify specificities of eye writing, as compared to handwriting, and the resulting technical challenges.

No MeSH data available.


Related in: MedlinePlus

Novelty detection during character recognition. Left column: evolutions of the probability distributions over characters (among “x,” “y,” “z,” and “$”), as the fourteenth first via-points are detected. Right column: final probability distribution over letters after detection of the fourteenth via-point. Top row concerns recognition and novelty detection when a “6” is presented: it is outside of the learning database and correctly recognized as a new character. Bottom row is when a “3” is presented: while outside of the learning database, it is geometrically close to a “z,” and incorrectly recognized as such, most of the time.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3822325&req=5

Figure 12: Novelty detection during character recognition. Left column: evolutions of the probability distributions over characters (among “x,” “y,” “z,” and “$”), as the fourteenth first via-points are detected. Right column: final probability distribution over letters after detection of the fourteenth via-point. Top row concerns recognition and novelty detection when a “6” is presented: it is outside of the learning database and correctly recognized as a new character. Bottom row is when a “3” is presented: while outside of the learning database, it is geometrically close to a “z,” and incorrectly recognized as such, most of the time.

Mentions: To experimentally test novelty recognition, we reduce our learning database to a subset of available characters: we only learn parameters for the “x,” “y,” and “z” characters. We then proceed with character recognition, and the system can only either recognize one of the three known characters, or the unknown character “$.” Figure 12 shows two illustrative examples of probability distributions for this small set of recognizable character, as the first 14 via-points are detected.


A Bayesian computational model for online character recognition and disability assessment during cursive eye writing.

Diard J, Rynik V, Lorenceau J - Front Psychol (2013)

Novelty detection during character recognition. Left column: evolutions of the probability distributions over characters (among “x,” “y,” “z,” and “$”), as the fourteenth first via-points are detected. Right column: final probability distribution over letters after detection of the fourteenth via-point. Top row concerns recognition and novelty detection when a “6” is presented: it is outside of the learning database and correctly recognized as a new character. Bottom row is when a “3” is presented: while outside of the learning database, it is geometrically close to a “z,” and incorrectly recognized as such, most of the time.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3822325&req=5

Figure 12: Novelty detection during character recognition. Left column: evolutions of the probability distributions over characters (among “x,” “y,” “z,” and “$”), as the fourteenth first via-points are detected. Right column: final probability distribution over letters after detection of the fourteenth via-point. Top row concerns recognition and novelty detection when a “6” is presented: it is outside of the learning database and correctly recognized as a new character. Bottom row is when a “3” is presented: while outside of the learning database, it is geometrically close to a “z,” and incorrectly recognized as such, most of the time.
Mentions: To experimentally test novelty recognition, we reduce our learning database to a subset of available characters: we only learn parameters for the “x,” “y,” and “z” characters. We then proceed with character recognition, and the system can only either recognize one of the three known characters, or the unknown character “$.” Figure 12 shows two illustrative examples of probability distributions for this small set of recognizable character, as the first 14 via-points are detected.

Bottom Line: Preliminary experimental results are presented, which illustrate the method, showing the feasibility of character recognition in the context of eye writing.We then show experimentally how a model of the unknown character can be used to detect trajectories that are likely to be new symbols, and how disability assessment can be performed by opportunistically observing characteristics of fine motor control, as letter are being traced.Experimental analyses also help identify specificities of eye writing, as compared to handwriting, and the resulting technical challenges.

View Article: PubMed Central - PubMed

Affiliation: Laboratoire de Psychologie et NeuroCognition, Université Grenoble Alpes-CNRS Grenoble, France.

ABSTRACT
This research involves a novel apparatus, in which the user is presented with an illusion inducing visual stimulus. The user perceives illusory movement that can be followed by the eye, so that smooth pursuit eye movements can be sustained in arbitrary directions. Thus, free-flow trajectories of any shape can be traced. In other words, coupled with an eye-tracking device, this apparatus enables "eye writing," which appears to be an original object of study. We adapt a previous model of reading and writing to this context. We describe a probabilistic model called the Bayesian Action-Perception for Eye On-Line model (BAP-EOL). It encodes probabilistic knowledge about isolated letter trajectories, their size, high-frequency components of the produced trajectory, and pupil diameter. We show how Bayesian inference, in this single model, can be used to solve several tasks, like letter recognition and novelty detection (i.e., recognizing when a presented character is not part of the learned database). We are interested in the potential use of the eye writing apparatus by motor impaired patients: the final task we solve by Bayesian inference is disability assessment (i.e., measuring and tracking the evolution of motor characteristics of produced trajectories). Preliminary experimental results are presented, which illustrate the method, showing the feasibility of character recognition in the context of eye writing. We then show experimentally how a model of the unknown character can be used to detect trajectories that are likely to be new symbols, and how disability assessment can be performed by opportunistically observing characteristics of fine motor control, as letter are being traced. Experimental analyses also help identify specificities of eye writing, as compared to handwriting, and the resulting technical challenges.

No MeSH data available.


Related in: MedlinePlus