University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Minimal Training, Large Lexicon, Unconstrained Sign Language Recognition

Kadir, T, Bowden, R, Ong, EJ and Zisserman, A (2004) Minimal Training, Large Lexicon, Unconstrained Sign Language Recognition In: BMVC 2004 - British Machine Vision Conference 7-9th Sept 2004, 2004-09-07 - 2004-09-09, Kingston University, London.

[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

This paper presents a flexible monocular system capable of recognising sign lexicons far greater in number than previous approaches. The power of the system is due to four key elements: (i) Head and hand detection based upon boosting which removes the need for temperamental colour segmentation; (ii) A body centred description of activity which overcomes issues with camera placement, calibration and user; (iii) A two stage classification in which stage I generates a high level linguistic description of activity which naturally generalises and hence reduces training; (iv) A stage II classifier bank which does not require HMMs, further reducing training requirements. The outcome of which is a system capable of running in real-time, and generating extremely high recognition rates for large lexicons with as little as a single training instance per sign. We demonstrate classification rates as high as 92% for a lexicon of 164 words with extremely low training requirements outperforming previous approaches where thousands of training examples are required.

Item Type: Conference or Workshop Item (Conference Paper)
Subjects : Computing
Divisions : Faculty of Engineering and Physical Sciences > Computing Science
Authors :
NameEmailORCID
Kadir, TUNSPECIFIEDUNSPECIFIED
Bowden, RUNSPECIFIEDUNSPECIFIED
Ong, EJUNSPECIFIEDUNSPECIFIED
Zisserman, AUNSPECIFIEDUNSPECIFIED
Date : 7 September 2004
Identification Number : 10.5244/C.18.96
Copyright Disclaimer : © BMVA 2004-07-30
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 26 Oct 2016 13:46
Last Modified : 31 Oct 2017 18:51
URI: http://epubs.surrey.ac.uk/id/eprint/812625

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800