Lancaster EPrints

HandsDown: hand-contour-based user identification for interactive surfaces

Schmidt, Dominik and Chong, Ming Ki and Gellersen, Hans (2010) HandsDown: hand-contour-based user identification for interactive surfaces. In: NordiCHI '10 Proceedings of the 6th Nordic Conference on Human-Computer Interaction: Extending Boundaries. ACM, New York, pp. 432-441. ISBN 978-1-60558-934-3

Full text not available from this repository.

Abstract

HandsDown is a novel technique for user identification on interactive surfaces. It enables users to access personal data on a shared surface, to associate objects with their identity, and to fluidly customize appearance, content, or functionality of the user interface. To identify, users put down their hand flat on the surface. HandsDown is based on hand contour analysis; neither user instrumentation nor external devices are required for identification. Characteristic features of the hand are initially extracted from images captured by the surface’s camera system and then classified using Support Vector Machines (SVM). We present a proof-of-concept implementation and show results of our evaluation which indicates the technique’s robustness for user identification within small groups. Additionally, we introduce a set of interaction techniques to illustrate how HandsDown can improve the user experience, and we discuss the design space of such interactions.

Item Type: Contribution in Book/Report/Proceedings
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: Faculty of Science and Technology > School of Computing & Communications
ID Code: 42500
Deposited By: ep_importer_comp
Deposited On: 01 Jul 2010 09:26
Refereed?: No
Published?: Published
Last Modified: 10 Apr 2014 01:02
Identification Number:
URI: http://eprints.lancs.ac.uk/id/eprint/42500

Actions (login required)

View Item