Automated labeling of ink stroke data

Authors:
Jacky (Shunjie) Zhen;Rachel Blagojevic;Beryl Plimmer
Affiliations:
University of Auckland, Auckland, New Zealand;University of Auckland, Auckland, New Zealand;University of Auckland, Auckland, New Zealand
Venue:
Proceedings of the International Symposium on Sketch-Based Interfaces and Modeling
Year:
2012

Citing 13
Cited 0

Specifying gestures by example

Proceedings of the 18th annual conference on Computer graphics and interactive techniques
Random Forests

Machine Learning
Logistic Model Trees

Machine Learning
iGesture: A General Gesture Recognition Framework

ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 02
A pen-based tool for efficient labeling of 2D sketches

SBIM '07 Proceedings of the 4th Eurographics workshop on Sketch-based interfaces and modeling
Automatic evaluation of sketch recognizers

Proceedings of the 6th Eurographics Symposium on Sketch-Based Interfaces and Modeling
Games for sketch data collection

Proceedings of the 6th Eurographics Symposium on Sketch-Based Interfaces and Modeling
Tools for the efficient generation of hand-drawn corpora based on context-free grammars

Proceedings of the 6th Eurographics Symposium on Sketch-Based Interfaces and Modeling
Intelligent diagramming in the electronic online classroom

HSI'09 Proceedings of the 2nd conference on Human System Interactions
Technical Section: The effect of task on classification accuracy: Using gesture recognition techniques in free-sketch recognition

Computers and Graphics
Rata.gesture: A gesture recognizer developed using data mining

Artificial Intelligence for Engineering Design, Analysis and Manufacturing
A data collection tool for sketched diagrams

SBM'08 Proceedings of the Fifth Eurographics conference on Sketch-Based Interfaces and Modeling
SOUSA: sketch-based online user study applet

SBM'08 Proceedings of the Fifth Eurographics conference on Sketch-Based Interfaces and Modeling

Quantified Score

Hi-index	0.00

Visualization

Abstract

Labeled ink stroke data is essential to the development and evaluation of sketch recognizers. Manually labeling strokes is a tedious, time-consuming, and error prone task; and very few tools are available to facilitate this. We propose a new and intuitive method of automatic labeling for single stroke primitives. This involves building a recognizer from a partially labeled dataset. This recognizer is then used to identify and automatically label the remaining data, therefore reducing the amount of manual labeling required by researchers. An evaluation comparing manual labeling against our new auto labeling method shows that users are able to label significantly faster and produce less errors using auto labeling. Furthermore, users found auto labeling easier and more preferable.