Effect of Initial HMM Choices in Multiple Sequence Training for Gesture Recognition

Liu, Nianjun, Davis, Richard I. A., Lovell, Brian C. and Kootsookos, Peter J. (2004). Effect of Initial HMM Choices in Multiple Sequence Training for Gesture Recognition. In: P. Srimani, Proceedings of the International Conference on Information Technology: Coding and Computing. International Conference on Information Technology (ITCC 2004), Las Vegas, Nevada, U.S.A., (608-613). 5-7 April, 2004. doi:10.1109/ITCC.2004.1286531

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
itccDavisLiuLove.pdf itccDavisLiuLove.pdf application/pdf 186.84KB 0

Author Liu, Nianjun
Davis, Richard I. A.
Lovell, Brian C.
Kootsookos, Peter J.
Title of paper Effect of Initial HMM Choices in Multiple Sequence Training for Gesture Recognition
Conference name International Conference on Information Technology (ITCC 2004)
Conference location Las Vegas, Nevada, U.S.A.
Conference dates 5-7 April, 2004
Proceedings title Proceedings of the International Conference on Information Technology: Coding and Computing
Journal name Itcc 2004: International Conference On Information Technology: Coding and Computing, Vol 1, Proceedings
Place of Publication Los Alamitos, California
Publisher The Institute of Electrical and Electronics Engineers Computer Society
Publication Year 2004
Sub-type Fully published paper
DOI 10.1109/ITCC.2004.1286531
Open Access Status File (Author Post-print)
ISBN 0-7695-2108-8
Editor P. Srimani
Volume 1
Start page 608
End page 613
Total pages 6
Language eng
Abstract/Summary We present several ways to initialize and train Hidden Markov Models (HMMs) for gesture recognition. These include using a single initial model for training (reestimation), multiple random initial models, and initial models directly computed from physical considerations. Each of the initial models is trained on multiple observation sequences using both Baum-Welch and the Viterbi Path Counting algorithm on three different model structures: Fully Connected (or ergodic), Left-Right, and Left-Right Banded. After performing many recognition trials on our video database of 780 letter gestures, results show that a) the simpler the structure is, the less the effect of the initial model, b) the direct computation method for designing the initial model is effective and provides insight into HMM learning, and c) Viterbi Path Counting performs best overall and depends much less on the initial model than does Baum-Welch training.
Subjects 280207 Pattern Recognition
E1
0899 Other Information and Computing Sciences
Keyword Iris-research
Gesture recognition
Hidden Markov models
Q-Index Code E1

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 2 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 11 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Wed, 23 Jun 2004, 10:00:00 EST by Brian C. Lovell on behalf of Faculty Of Engineering, Architecture & Info Tech