User and System Cross-Learning of Gesture Commands on Pen-Based Devices

Li, Peiyu; Bouillon, Manuel; Anquetil, Éric; Richard, Grégoire

doi:10.1007/978-3-642-40480-1_21

Cited by 4 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve gesture command recognition, the classifier learns incrementally during its use. At the same time that the classifier is learning, so is the user: he has to memorize which gesture is associated with which command [4]. In this cross-learning situation, different cases can happen:…”

Section: The Intuisup Supervisormentioning

confidence: 99%

See 1 more Smart Citation

Online active supervision of an evolving classifier for customized-gesture-command learning

Bouillon

Anquetil

2017

Neurocomputing

Self Cite

View full text Add to dashboard Cite

To cite this version:Manuel Bouillon, Eric Anquetil.Online active supervision of an evolving classifier for customized-gesture-command learning.Neurocomputing AbstractTouch sensitive interfaces enable new interaction methods, like gesture commands. For users to easily memorize more than a dozen of gesture commands, it is important to enable gesture set customization. The classifier used to recognize drawn symbols must hence be customizable -able to learn from very few data -and evolving -able to learn new classes on-the-fly and improve during its use. The objective of this work is to obtain a gesture command system that cooperates as best as possible with the user: that learns from its mistakes without soliciting the user too often. This paper presents a novel approach for the online active learning of gesture commands, with three contributions. The IntuiSup supervisor monitors the learning process and user interactions. The Evolving Sampling by Uncertainty (ESU) algorithm enables to maintain the error/interaction compromise over time. The Boosted-ESU (B-ESU) method optimizes interaction impact to fasten system learning speed. The efficiency of our approach is evaluated on the publicly available ILG Data Base of gesture commands. Experimentation shows the effectiveness of the supervision strategy and improvements both in term of accuracy and learning speed.

show abstract

Section: The Intuisup Supervisormentioning

confidence: 99%

“…Those gesture commands [1,2] enable users to execute various actions simply by drawing the associated symbols. Previous studies [3,4] have shown that enabling customization is essential to help user memorization of gestures. In order to use such gesture commands, a handwritten gesture recognition system is required.…”

Section: Introductionmentioning

confidence: 99%

Online active supervision of an evolving classifier for customized-gesture-command learning

Bouillon

Anquetil

2017

Neurocomputing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Li et al presented in their second experiment a way to help the user to learn the gestures [9]. To get help, the user has to activate a widget that shows each command and the related pen-based gesture.…”

Section: Related Workmentioning

confidence: 99%

Improving In-game Gesture Learning with Visual Feedback

Schwaller

Kühni

Angelini

et al. 2014

Human-Computer Interaction. Applications and Services

View full text Add to dashboard Cite

Abstract. This paper presents a research work on gesture recognition and feedback to reduce the learning time of new gestures and to augment user performance in a game application. A Wiimote controlled space shooter game, GeStar Wars, has been developed. The player controls a spaceship through the buttons in the controller, while forearm gestures can be used to perform special actions. Gesture strokes are mapped in a 3x3 grid and are differentiated according to the path of the covered grid cells. In-game visual feedback displays to the user the current gesture path and which cells were covered after the gesture is performed. The novelty of this research resides in the correlated gesture recognition methodology and feedback which helps the user to learn and correct the gestures. The evaluation, conducted with 12 users, showed that the users performed significantly better if feedback was provided.

show abstract

“…Those gesture commands [1][2] enable users to execute various actions simply by drawing symbols. Previous studies [3] [4] have shown that enabling customization is essential to help user memorization of gestures. To use such gesture commands, a handwritten gesture recognition system is required.…”

Section: Introductionmentioning

confidence: 99%

Supervision Strategies for the Online Learning of an Evolving Classifier for Gesture Commands

Bouillon

Anquetil

2014

2014 22nd International Conference on Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Touch sensitive interfaces enable new interaction methods like using gesture commands. To easily memorize more than a dozen of gesture commands, it is important to be able to customize them. The classifier used to recognize drawn symbols must hence be customisable, able to learn from very few data, and evolving, able to learn and improve during its use. This work studies different supervision strategies for the online training of the evolving classifier. We compare six supervision strategies, depending on user interaction (solicitation by the system), and self-evaluation capacities (notion of reject). In particular, there is a trade-off between the number of user interactions, to supervise the online training, and the error rate of the classifier. We show in this paper that the strategy giving the best results is to learn from data validated by the user, when the confidence of the recognition is too low, and from data implicitly validated.

show abstract

User and System Cross-Learning of Gesture Commands on Pen-Based Devices

Cited by 4 publications

References 16 publications

Online active supervision of an evolving classifier for customized-gesture-command learning

Online active supervision of an evolving classifier for customized-gesture-command learning

Improving In-game Gesture Learning with Visual Feedback

Supervision Strategies for the Online Learning of an Evolving Classifier for Gesture Commands

Contact Info

Product

Resources

About