Mode detection in on-line pen drawing and handwriting recognition

Willems, D.J.M.; Rossignol, Stéphane; Vuurpijl, L.G.

doi:10.1109/icdar.2005.160

Cited by 16 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The probability table for each classifier node is determined by testing the classifier on the data set and is equal to the confusion matrix of the classifier. The four classifiers use kNN (with k=3, determined by trial an error), using all geometric features presented in [11,12].…”

Section: A Bayesian Network For Combining Multiple Information Resourcesmentioning

confidence: 99%

“…Unfortunately, when users are unconstrained in the types of gestures that they can use, recognition becomes problematic. In a recognition system that needs to recognize not only different gestures, but also the type (or mode) of the pen gestures, mode detection [3,7] is employed before specific classifiers are used for actual recognition [12]. Mode detection should for instance be able to determine whether a user is producing deictic gestures (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…Using geometrical features with kNN and MLP classifiers we were able to obtain a performance of 98.7% for mode detection between handwritten text, arrows, lines, and geometric objects [11]. Using a hierarchical mode detection system and expanding the recognized classes to include four geometric shapes, an overall performance of 95.6% was reached [12]. The problem with these mode detection systems was that they were trained and tested using data that was not obtained from the crisis management domain.…”

Section: Introductionmentioning

confidence: 99%

“…The mode detection systems we presented in [12] was tested with the new domain specific data set that resulted from the human factors experiment. As expected the performance was not good.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Bayesian Network Approach to Mode Detection for Interactive Maps

Willems

Vuurpijl

2007

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2

Self Cite

View full text Add to dashboard Cite

This paper describes a mode detection system for online pen input that employs a Bayesian network to combine classification results and context information. Previous monolithic classifiers were not able to provide sufficient performance to be used in the domain of crisis management, where robust interaction is extremely important. To enhance mode detection for the intended target domain of crisis management, domain specific pen gesture data was used to train the four different classifiers and to calculate the conditional probabilities used in the Bayesian network. Mode detection, which is used to distinguish between different types of pen input such as deictic gestures, handwritten text, and iconic objects, clearly profited from this new approach. The error rate dropped from 9.3% for a monolithic system to 4.0% for the new mode detection system.

show abstract

Section: A Bayesian Network For Combining Multiple Information Resourcesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The mode detection systems we presented in [12] was tested with the new domain specific data set that resulted from the human factors experiment. As expected the performance was not good.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Bayesian Network Approach to Mode Detection for Interactive Maps

Willems

Vuurpijl

2007

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2

Self Cite

View full text Add to dashboard Cite

show abstract

“…To formulate the single-site likelihood potential, 11 features, which have been mentioned in [9], are extracted from each stroke. They are the stroke length, area, compactness, eccentricity, circular variance, rectangularity, centroid offset along major axis, closure, absolute curvature, perpendicularity, and signed perpendicularity.…”

Section: Stroke Featuresmentioning

confidence: 99%

Text/Non-text Ink Stroke Classification in Japanese Handwriting Based on Markov Random Fields

Zhou¹,

Liu²

2007

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)

View full text Add to dashboard Cite

show abstract

Design Issues for Pen-Centric Interactive Maps

Vuurpijl

Willems

Niels

et al. 2010

Interactive Collaborative Information Systems

View full text Add to dashboard Cite

The following full text is a publisher's version.For additional information about this publication click this link. http://hdl.handle.net/2066/83795Please be advised that this information was generated on 2024-06-03 and may be subject to change. Article 25fa End User AgreementThis publication is distributed under the terms of Article 25fa of the Dutch Copyright Act. This article entitles the maker of a short scientific work funded either wholly or partially by Dutch public funds to make that work publicly available for no consideration following a reasonable period of time after the work was first published, provided that clear reference is made to the source of the first publication of the work.Research outputs of researchers employed by Dutch Universities that comply with the legal requirements of Article 25fa of the Dutch Copyright Act, are distributed online and free of cost or other barriers in institutional repositories. Research outputs are distributed six months after their first online publication in the original published version and with proper attribution to the source of the original publication.

show abstract

Mode detection in on-line pen drawing and handwriting recognition

Cited by 16 publications

References 15 publications

A Bayesian Network Approach to Mode Detection for Interactive Maps

A Bayesian Network Approach to Mode Detection for Interactive Maps

Text/Non-text Ink Stroke Classification in Japanese Handwriting Based on Markov Random Fields

Design Issues for Pen-Centric Interactive Maps

Contact Info

Product

Resources

About