Template based classification of multi-touch gestures

Authors:
Michael Schmidt;Gerhard Weber
Affiliations:
Dresden University of Technology, Institute of Applied Science, Human-Computer Interaction, Nöthnitzer Straíe 46, 01062 Dresden, Germany;Dresden University of Technology, Institute of Applied Science, Human-Computer Interaction, Nöthnitzer Straíe 46, 01062 Dresden, Germany
Venue:
Pattern Recognition
Year:
2013

Citing 15
Cited 1

Specifying gestures by example

Proceedings of the 18th annual conference on Computer graphics and interactive techniques
Combining gestures and direct manipulation

CHI '92 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
The automatic recognition of gestures

The automatic recognition of gestures
Pen computing for air traffic control

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
The immediate usability of graffiti

Proceedings of the conference on Graphics interface '97
The Softassign Procrustes Matching Algorithm

IPMI '97 Proceedings of the 15th International Conference on Information Processing in Medical Imaging
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Robust sketched symbol fragmentation using templates

Proceedings of the 9th international conference on Intelligent user interfaces
Gestures without libraries, toolkits or training: a $1 recognizer for user interface prototypes

Proceedings of the 20th annual ACM symposium on User interface software and technology
Slide rule: making mobile touch screens accessible to blind people using multi-touch interaction techniques

Proceedings of the 10th international ACM SIGACCESS conference on Computers and accessibility
User-defined gestures for surface computing

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
SOMM: Self organizing Markov map for gesture recognition

Pattern Recognition Letters
Trainable sketch recognizer for graphical user interface design

INTERACT'07 Proceedings of the 11th IFIP TC 13 international conference on Human-computer interaction
A lightweight multistroke recognizer for user interface prototypes

Proceedings of Graphics Interface 2010
Enhancing single touch gesture classifiers to multitouch support

ICCHP'10 Proceedings of the 12th international conference on Computers helping people with special needs

Recognition of multi-touch drawn sketches

HCI'13 Proceedings of the 15th international conference on Human-Computer Interaction: interaction modalities and techniques - Volume Part IV

Quantified Score

Hi-index	0.01

Visualization

Abstract

We propose a probabilistic classifier for multi-touch gestures specified by users themselves. The template-based gesture classifier allows selecting gesture types more freely without constraints regarding implementation issues and considers multi-finger or bi-manual operations. The statistical approaches to the classification scheme are presented. The basic concepts of separating input into tokens, retrieving local features and applying a new method of sensor fusion under uncertainty are adaptive to broader application ranges. Results from testing against a set of sophisticated samples show that this approach performs well and, while recognition benefits from more complex gestures, it also distinguishes subtly different gestures.