Author

Publication

2004 - , Ontario

Language

English

Word Count

25,750 words, Guess

Page Count

103 pages

Identifiers

  • ISBN-100612913228
  • ISBN-139780612913226
  • Open LibraryOL19746769M

Description

This thesis presents two related research projects exploring gesture-based interaction. The VisionWand system explores a passive wand tracked in 3D using computer vision techniques as a new input mechanism for interacting with large displays. A variety of gesture-based interaction techniques is designed to exploit the affordances of the wand, resulting in an effective alternative interface for large display interaction. Inspired by the observations made in the VisionWand and similar gesture-based interaction systems that different users have different habits in making gestures and performing tasks, we developed the adaptive gesture interface as a framework that exploits machine learning techniques to capture and utilize the users' habits on line. This framework improved the system's performance of gesture recognition, and alleviated the user's need for practice. We present a rigorous user experiment to demonstrate this improvement.

Subjects

Links

Reader Reviews

No reviews yet for this book.

Be the first to share your thoughts!